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 agentmods add skills/kalpmodi/akira/cloud-auditnpx skills add kalpmodi/akira --skill cloud-auditgit clone --depth 1 https://github.com/kalpmodi/akiraWrote 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/kalpmodi/akira/cloud-audit)<a href="https://agentmods.dev/skills/kalpmodi/akira/cloud-audit"><img src="https://agentmods.dev/badge/skills/kalpmodi/akira/cloud-audit.svg" alt="Measured on agentmods" 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 | $0.00097 | $0.05629 |
| Opus 5 | $0.00048 | $0.02815 |
| Sonnet 5 | $0.00019 | $0.01126 |
| Haiku 4.5 | $0.00010 | $0.00563 |
Grade D, and why
cloud-audit scanned grade D with 4 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 6d 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.
Reaches for credential filesmediumPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
-d "cmd=cat /etc/shadow" Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl http://<etcd-ip>:2379/v2/keys/?recursive=true | python3 -m json.tool | grep -i "secret\|token\|password" 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.
One SSRF to 169.254.169.254 = IAM creds = all S3 = all Secrets Manager = game over. 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 -sI https://<target> | grep -i "server\|via\|x-amz\|x-goog\|x-ms-" How it starts
The opening of the file, as written. The whole thing — 518 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloud Infrastructure Audit Playbook
Philosophy
Cloud misconfigs are the highest-signal, lowest-effort findings in modern pentests. One SSRF to 169.254.169.254 = IAM creds = all S3 = all Secrets Manager = game over. Never claim "cloud compromise" without demonstrating actual data access with real credentials.
Arguments
<target> - domain or AWS account ID
<focus> - optional: AWS / GCP / AZURE / K8S / FULL
Phase 0: Smart Intake
source ~/.claude/skills/_shared/phase0.sh
source ~/.claude/skills/_shared/signals.sh
p0_init_vars "$1"
p0_state_gate "HARVEST" || exit 0
p0_read_relay recon secrets exploit
p0_read_memory
p0_read_hypotheses
AWS_KEYS=$AWS_KEYS_FOUND # alias to match downstream references
echo "=== PHASE 0 CLOUD-AUDIT INTAKE: $TARGET ==="
echo "State: $STATE"
echo "AWS keys found: $AWS_KEYS | SSRF vectors: $(echo "$SSRF_VECTORS" | wc -l)"
echo "AWS/GCP/Azure hints: $AWS_HINT/$GCP_HINT/$AZURE_HINT"
echo "ATW flagged (avoid): ${ATW_FLAGGED:-none}"
Execution Manifest
# Manifest is dynamic: only include phases for confirmed cloud providers
# MUST items = confirmed via prior intel. SHOULD = hinted. IF_TIME = speculative.
MANIFEST=$(cat << 'MANIFEST_EOF'
{
"phase": "cloud-audit",
"generated_at": "YYYY-MM-DD HH:MM",
"items": [
{"id":"c01","tool":"cloud-footprint-discovery","target":"<target>","reason":"identify cloud provider from DNS/headers","priority":"MUST","status":"pending","skip_reason":null},
{"id":"c02","tool":"s3-bucket-enum","target":"<target-brand>","reason":"find exposed S3/GCS/Azure blob buckets","priority":"MUST","status":"pending","skip_reason":null},
{"id":"c03","tool":"imds-ssrf","target":"<ssrf-endpoint-from-exploit-relay>","reason":"SSRF->IMDS credential theft if SSRF_VECTORS found","priority":"MUST","status":"pending","skip_reason":"set to skipped if no SSRF_VECTORS"},
{"id":"c04","tool":"aws-iam-enum","target":"credentials from SSRF or secrets","reason":"enumerate IAM permissions, privesc paths","priority":"MUST","status":"pending","skip_reason":"set to skipped if no AWS credentials"},
{"id":"c05","tool":"aws-data-exfil","target":"S3/SecretsManager/SSM/Lambda","reason":"extract actual sensitive data to prove impact","priority":"MUST","status":"pending","skip_reason":null},
{"id":"c06","tool":"gcp-metadata-enum","target":"<ssrf-endpoint>","reason":"GCP SA token via metadata if GCP_HINT=true","priority":"SHOULD","status":"pending","skip_reason":"skip if GCP_HINT=false"},
{"id":"c07","tool":"azure-imds","target":"<ssrf-endpoint>","reason":"Azure managed identity token if AZURE_HINT=true","priority":"SHOULD","status":"pending","skip_reason":"skip if AZURE_HINT=false"},
{"id":"c08","tool":"k8s-api-probe","target":"<live-hosts>:6443","reason":"exposed K8s API server","priority":"IF_TIME","status":"pending","skip_reason":null},
{"id":"c09","tool":"cloud-misconfiguration-checklist","target":"<account>","reason":"IAM wildcard, SGgroups, CloudTrail disabled","priority":"SHOULD","status":"pending","skip_reason":null}
]
}
MANIFEST_EOF
)
jq --argjson m "$MANIFEST" '.scalpel.active_manifest = $m' $SESSION > /tmp/s.json && mv /tmp/s.json $SESSION
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.
- 6d ago First seen · 518 lines · 97 tokens per session scan D 4f294c120f70
cloud-audit is a skill published in the GitHub repository kalpmodi/akira (21 stars, last pushed 1mo ago), licensed MIT. It adds 97 tokens to every session and 5,629 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it D with 4 findings (reaches for credential files, downloads and executes remote code, cloud metadata endpoint). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
conducting-cloud-penetration-testing
This skill outlines methodologies for performing authorized penetration testing against AWS, Azure, and GCP cloud environments. It covers understanding the shared responsibility model for testing scope, leveraging cloud-specific attack tools like Pacu and ScoutSuite, exploiting IAM misconfigurations, testing for SSRF…
performing-kubernetes-penetration-testing
Kubernetes penetration testing systematically evaluates cluster security by simulating attacker techniques against the API server, kubelet, etcd, pods, RBAC, network policies, and secrets. Using tools.
conducting-cloud-penetration-testing
This skill outlines methodologies for performing authorized penetration testing against AWS, Azure, and GCP cloud environments. It covers understanding the shared responsibility model for testing scope, leveraging cloud-specific attack tools like Pacu and ScoutSuite, exploiting IAM misconfigurations, testing for SSRF…
conducting-cloud-penetration-testing
This skill outlines methodologies for performing authorized penetration testing against AWS, Azure, and GCP cloud environments. It covers understanding the shared responsibility model for testing scope, leveraging cloud-specific attack tools like Pacu and ScoutSuite, exploiting IAM misconfigurations, testing for SSRF…
cloudflare-temporary-deploy
Deploy a Worker live, no account, via wrangler --temporary.
tensorrt-llm
High-throughput LLM inference on NVIDIA GPUs.