Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mukul975/Threatswarmnpx agentmods add agents/mukul975/threatswarm/cloud-attackerWrote 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/agents/mukul975/threatswarm/cloud-attacker)<a href="https://agentmods.dev/agents/mukul975/threatswarm/cloud-attacker"><img src="https://agentmods.dev/badge/agents/mukul975/threatswarm/cloud-attacker/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/agents/mukul975/threatswarm/cloud-attacker"><img src="https://agentmods.dev/badge/agents/mukul975/threatswarm/cloud-attacker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00086 | $0.03229 |
| Opus 5.5 | $0.00034 | $0.01292 |
| Sonnet 5.5 | $0.00017 | $0.00646 |
| Haiku 4.5 | $0.00009 | $0.00323 |
Grade C, and why
cloud-attacker scanned grade C with 3 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 1mo 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.
Harvests environment variablesmediumData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
# run secrets__manager -- dump Secrets Manager Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Cloud metadata endpointmediumServer-side request forgery
One request to 169.254.169.254 can return temporary IAM credentials.
curl -s http://169.254.169.254/latest/meta-data/ 2>&1 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 -s http://169.254.169.254/latest/meta-data/ 2>&1 How it starts
The opening of the file, as written. The whole thing — 284 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cybersecurity Skills (Invoke First)
Before starting cloud testing, invoke these skills via the Skill tool:
cybersecurity-skills:conducting-cloud-penetration-testingcybersecurity-skills:performing-cloud-penetration-testing-with-pacucybersecurity-skills:performing-aws-privilege-escalation-assessmentcybersecurity-skills:auditing-aws-s3-bucket-permissionscybersecurity-skills:auditing-gcp-iam-permissionscybersecurity-skills:performing-aws-account-enumeration-with-scout-suite
Scope Enforcement
Verify cloud account IDs, subscription IDs, or project IDs are listed in scope.txt. Cloud APIs can affect resources across accounts/regions — confirm authorization explicitly. Never modify production resources — read-only enumeration first.
AWS Enumeration
Identity & Initial Access
# Verify current caller identity
aws sts get-caller-identity 2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/cloud/aws_identity.json
# List all enabled regions
aws ec2 describe-regions --query 'Regions[].RegionName' --output text 2>&1
# Enumerate IAM users
aws iam list-users --query 'Users[*].[UserName,UserId,Arn,CreateDate]' \
--output table 2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/cloud/aws_users.txt
# List IAM roles
aws iam list-roles --query 'Roles[*].[RoleName,Arn,AssumeRolePolicyDocument]' \
--output json 2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/cloud/aws_roles.json
# List IAM policies (customer-managed)
aws iam list-policies --scope Local \
--query 'Policies[*].[PolicyName,Arn,AttachmentCount]' \
--output table 2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/cloud/aws_policies.txt
# Get all policies attached to a user
aws iam list-attached-user-policies --user-name $USER 2>&1
aws iam list-user-policies --user-name $USER 2>&1
aws iam simulate-principal-policy \
--policy-source-arn $(aws sts get-caller-identity --query Arn --output text) \
--action-names "iam:CreateUser" "iam:AttachRolePolicy" "s3:PutBucketPolicy" \
--output json 2>&1 | tee evidence/$(date +%Y%m%d)/$TARGET/cloud/aws_perms.json
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.
- 1mo ago First seen · 284 lines · 0 tokens per session scan C 4cf6603eed51
cloud-attacker is an agent published in the GitHub repository mukul975/Threatswarm (89 stars, last pushed 5mo ago), licensed MIT. It adds 86 tokens to every session and 3,229 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it C with 3 findings (harvests environment variables, cloud metadata endpoint, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
web3-auditor
Smart contract security auditor. Checks 10 bug classes in order of frequency (accounting desync 28%, access control 19%, incomplete path 17%, off-by-one 22% of Highs, oracle errors, ERC4626 attacks, reentrancy, flash loan oracle manipulation, signature replay, proxy/upgrade issues). Applies pre-dive kill signals…
osint-collector
Delegates to this agent when the user asks about OSINT, reconnaissance, information gathering, target profiling, email harvesting, subdomain enumeration, social media recon, breach data, open source intelligence, or building a target dossier for authorized engagements.
llm-redteam
Delegates to this agent when the user asks about LLM and AI system red teaming, prompt injection (direct and indirect), jailbreak techniques, RAG poisoning, model exfiltration, training data extraction, agent and tool-use abuse, MCP server exploitation, AI guardrail bypass, or red teaming a deployed…
malware-analyst
Delegates to this agent when the user asks about malware analysis, reverse engineering, binary analysis, disassembly, debugging, sandbox analysis, static analysis, dynamic analysis, or suspicious file triage.
compliance-mapper
Delegates to this agent when the user wants to map penetration-test findings to compliance frameworks — PCI DSS, NIST 800-53 / CSF, ISO 27001, CIS Controls, HIPAA, SOC 2 — produce control-gap analysis, and translate technical findings into compliance impact. Distinct from stig-analyst (STIG hardening) and…
detection-engineer
Delegates to this agent when the user asks about detection rules, SIEM queries, threat hunting, indicator analysis, log analysis, blue team detection for specific attack techniques, or creating detection engineering content.