Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add adriannoes/awesome-agentic-ai --skill cloud-iam-deepgit clone --depth 1 https://github.com/adriannoes/awesome-agentic-aiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/adriannoes/awesome-agentic-ai/cloud-iam-deep)<a href="https://agentmods.dev/skills/adriannoes/awesome-agentic-ai/cloud-iam-deep"><img src="https://agentmods.dev/badge/skills/adriannoes/awesome-agentic-ai/cloud-iam-deep/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/adriannoes/awesome-agentic-ai/cloud-iam-deep"><img src="https://agentmods.dev/badge/skills/adriannoes/awesome-agentic-ai/cloud-iam-deep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 12 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Server-Side Request Forgery · line 158 Code accesses a cloud instance metadata endpoint (e.g. 169.254.169.254). A single request can return temporary IAM credentials, making this a high-value SSRF target for credential theft.Fix: Remove access to cloud metadata endpoints unless strictly required. If metadata is needed, restrict it (e.g. IMDSv2 with hop limit) and never expose returned credentials.
- high Server-Side Request Forgery · line 161 Code accesses a cloud instance metadata endpoint (e.g. 169.254.169.254). A single request can return temporary IAM credentials, making this a high-value SSRF target for credential theft.Fix: Remove access to cloud metadata endpoints unless strictly required. If metadata is needed, restrict it (e.g. IMDSv2 with hop limit) and never expose returned credentials.
- high Server-Side Request Forgery · line 165 Code accesses a cloud instance metadata endpoint (e.g. 169.254.169.254). A single request can return temporary IAM credentials, making this a high-value SSRF target for credential theft.Fix: Remove access to cloud metadata endpoints unless strictly required. If metadata is needed, restrict it (e.g. IMDSv2 with hop limit) and never expose returned credentials.
- high Server-Side Request Forgery · line 167 Code accesses a cloud instance metadata endpoint (e.g. 169.254.169.254). A single request can return temporary IAM credentials, making this a high-value SSRF target for credential theft.Fix: Remove access to cloud metadata endpoints unless strictly required. If metadata is needed, restrict it (e.g. IMDSv2 with hop limit) and never expose returned credentials.
- high Server-Side Request Forgery · line 207 Code accesses a cloud instance metadata endpoint (e.g. 169.254.169.254). A single request can return temporary IAM credentials, making this a high-value SSRF target for credential theft.Fix: Remove access to cloud metadata endpoints unless strictly required. If metadata is needed, restrict it (e.g. IMDSv2 with hop limit) and never expose returned credentials.
- high Server-Side Request Forgery · line 209 Code accesses a cloud instance metadata endpoint (e.g. 169.254.169.254). A single request can return temporary IAM credentials, making this a high-value SSRF target for credential theft.Fix: Remove access to cloud metadata endpoints unless strictly required. If metadata is needed, restrict it (e.g. IMDSv2 with hop limit) and never expose returned credentials.
- high Server-Side Request Forgery · line 217 Code accesses a cloud instance metadata endpoint (e.g. 169.254.169.254). A single request can return temporary IAM credentials, making this a high-value SSRF target for credential theft.Fix: Remove access to cloud metadata endpoints unless strictly required. If metadata is needed, restrict it (e.g. IMDSv2 with hop limit) and never expose returned credentials.
- high Server-Side Request Forgery · line 221 Code accesses a cloud instance metadata endpoint (e.g. 169.254.169.254). A single request can return temporary IAM credentials, making this a high-value SSRF target for credential theft.Fix: Remove access to cloud metadata endpoints unless strictly required. If metadata is needed, restrict it (e.g. IMDSv2 with hop limit) and never expose returned credentials.
- high Tool Misuse · line 293 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Server-Side Request Forgery · line 294 Code accesses a cloud instance metadata endpoint (e.g. 169.254.169.254). A single request can return temporary IAM credentials, making this a high-value SSRF target for credential theft.Fix: Remove access to cloud metadata endpoints unless strictly required. If metadata is needed, restrict it (e.g. IMDSv2 with hop limit) and never expose returned credentials.
- high Privilege Escalation · line 296 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high YARA Match · line 346 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00198 | $0.04766 |
| Opus 5 | $0.00099 | $0.02383 |
| Sonnet 5 | $0.00040 | $0.00953 |
| Haiku 4.5 | $0.00020 | $0.00477 |
Grade B, and why
cloud-iam-deep scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Cloud metadata endpointmediumServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
curl http://169.254.169.254/latest/meta-data/iam/security-credentials/ Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://169.254.169.254/latest/meta-data/iam/security-credentials/ How it starts
The opening of the file, as written. The whole thing — 414 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use
Trigger when:
- A cloud credential surfaces (key, secret, token, JSON file)
- SSRF chain reaches IMDS / metadata endpoint
- APK / git-leak reveals embedded cloud key
- Recon shows public S3/GCS/Azure-blob with permissions you can verify
- A Kubernetes API or service-account token is exposed
- Post-RCE on a cloud-hosted instance — pivot to cloud control plane
Do NOT use for:
- On-prem-only environments (use AD attack skills — but those are out of scope per external-only boundary)
- Web2 vulns that happen to be on AWS — use the relevant
hunt-*skill
Credential identification (first 60 seconds)
# AWS access key patterns
AKIA[0-9A-Z]{16} # IAM user access key (long-term)
ASIA[0-9A-Z]{16} # STS temporary credential
AGPA[0-9A-Z]{16} # IAM group
AIDA[0-9A-Z]{16} # IAM user (user-id)
AROA[0-9A-Z]{16} # IAM role
ANPA[0-9A-Z]{16} # Managed policy
# AWS secret pattern (40-char base64-ish — context required)
[A-Za-z0-9/+=]{40} # AWS secret access key
# Azure
AccountKey=[A-Za-z0-9+/=]{86} # Storage account key
client_secret pattern + UUID # Azure AD app credential
# GCP service account JSON
{
"type": "service_account",
"project_id": "...",
"private_key_id": "...",
"private_key": "-----BEGIN PRIVATE KEY-----..."
}
# K8s SA token (JWT format — decode to confirm)
eyJhbGciOiJSUzI1... # decode kid claim to see issuer
AWS — read-only validation (the safe first step)
# Set credential
export AWS_ACCESS_KEY_ID="AKIA..."
export AWS_SECRET_ACCESS_KEY="..."
# 1. WHO am I?
aws sts get-caller-identity
# Returns: UserId, Account, Arn
# Arn tells you: IAM user vs role, account ID, name
# 2. WHAT can I do? (the privesc question)
# Try common read-only first — failures still inform you
aws iam list-users 2>&1 | head -5
aws iam list-roles 2>&1 | head -5
aws iam list-policies 2>&1 | head -5
aws iam list-groups 2>&1 | head -5
# 3. WHAT policies are attached to me?
aws iam list-attached-user-policies --user-name <self>
aws iam list-user-policies --user-name <self> # inline policies
aws iam list-groups-for-user --user-name <self>
# 4. Service-by-service surface
aws ec2 describe-instances --max-items 1 2>&1 | head
aws s3 ls 2>&1 | head -10
aws lambda list-functions --max-items 5 2>&1 | head
aws rds describe-db-instances --max-items 5 2>&1 | head
aws secretsmanager list-secrets --max-results 5 2>&1 | head
aws ssm describe-parameters --max-results 5 2>&1 | head
# 5. Audit any cross-account / external trust
aws iam list-roles --query 'Roles[?contains(AssumeRolePolicyDocument.Statement[0].Principal.AWS, `arn:aws:iam::`)]' 2>&1 | head -20
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 414 lines · 198 tokens per session scan B 64bb78f9a5d0
cloud-iam-deep is a skill published in the GitHub repository adriannoes/awesome-agentic-ai (57 stars, last pushed 14d ago), licensed MIT. It adds 198 tokens to every session and 4,766 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it B with 2 findings (cloud metadata endpoint, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
importing-a-codebase
Use when the repo holds real source code but no specs: the existing-codebase branch of setting-up-a-project, normally reached via that dispatcher, directly only when the situation is unmistakable. Not for empty workspaces (starting-a-new-project) or feature work in a specced project (brainstorming).
starting-a-new-project
Use when the workspace is empty — no code yet — and the user brings a raw idea: the brand-new branch of setting-up-a-project, normally reached via that dispatcher, directly only when the situation is unmistakable. Not for features in an existing project — use brainstorming instead.
todos
This chat has a shared, live TODO plan — your tasks for the conversation, which the user also edits. Read this skill and reach for the todo tools whenever a request takes more than a couple of steps. It covers the plan model (group = task, items = its steps; loose items are the user's lane), how to work it: propose…
writing-workflow-skills
Use when adding a new workflow skill to pi-thinkrail-workflow, changing an existing workflow skill's role, trigger, handoff, or structure, or checking a workflow skill against the workflow system's rules. Not for authoring general-purpose skills outside this package.
brainstorming
Use this BEFORE any creative or feature work: building a new feature, adding functionality, changing behavior, or making a nontrivial design decision. Turns the user's request into a validated design — recorded as a spec-graph task-spec — before any implementation. Do not skip this because a change looks small.
reviewing-changes
Use when a review package asks you to review a plan step's change set (todo.startReview): you are the REVIEWER, not the author. How to judge an agent-written diff, file findings with addreviewcomment, and settle with exactly one reviewverdict.