SKILLEMALL.ai
GitHub ↗ RU Sign in

BF cloud-iam-deep

Cloud IAM red-team attack chain across AWS, Azure, GCP — focused on EXTERNAL exploitation paths and post-credential-discovery privilege analysis. Covers IAM enumeration (aws iam, az role, gcloud iam), STS/AssumeRole chaining, Azure Managed Identity abuse (via SSRF/leak), GCP service account JSON abuse, IMDSv1/v2 attacks via SSRF, K8s ServiceAccount token privilege analysis once held (token discovery / cluster exposure is owned by hunt-k8s), role-trust-policy confused-deputy, cross-account assume-role enumeration, IAM privilege escalation patterns (24+ AWS, 8+ Azure, 6+ GCP), and AWS Cognito Identity Pool unauthenticated-role attack chain (GetId → GetCredentialsForIdentity → IAM role abuse). Built for the case where recon yields a credential (key, JSON, token) and you need to know what it grants and how to escalate. Use when an AWS key / Azure secret / GCP service account JSON / K8s SA token surfaces from a code repo, JS bundle, APK, breach corpus, or SSRF chain.

elementalsouls/Claude-BugHunter Agent Skills author: elementalsouls 1 file body ≈ 6 047 tokens Open the sourcegithub.com↗ analyzed 2 h ago

Cloud IAM red-team attack chain across AWS, Azure, GCP — focused on EXTERNAL exploitation paths and post-credential-discovery privilege analysis.

As a process F 48/100 · Will not run — References files that are not bundled: [a-z]{2}-[a-z]+-[0-9]:[0-9a-f-]{36}

ProcedureKubernetesAWSGoogle CloudAzureInfrastructuretype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
B
80/100
safety, quality, tests
Safety 60%
88
Quality 40%
67
Run on models
none yet
Process rating
F
48/100
Will not run
References files that are not bundled: [a-z]{2}-[a-z]+-[0-9]:[0-9a-f-]{36}
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
  2. The text references files that are not there: add them or drop the references.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 12

✓ No critical or high findings

Medium and low: 12
  • low Risky intent intent-offensive-security SKILL.md:3
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    description: Cloud IAM red-team attack chain across AWS, Azure, GCP — focused on EXTERNAL exploitation paths and post-credential-discovery privilege analysis. Covers IAM enumeration (aws iam, az role,
  • low Secrets in code secret-private-key SKILL.md:47
    Private key material (placeholder value)
    "private_key": "-----BEGIN PRIVATE KEY----- …
    placeholder
  • low Risky intent intent-offensive-security SKILL.md:68
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    # 2. WHAT can I do? (the privesc question)
  • low Risky intent intent-offensive-security SKILL.md:94
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ## AWS privesc patterns (24+ documented — `iam_privesc` techniques)
  • low Secrets in code secret-high-entropy-token SKILL.md:165
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    curl -X PUT "http://169.254.169.254/latest/api/token" -H "X-aw…ds: 21600"
    quoted
  • low Exfiltration net-credential-use SKILL.md:167
    Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)
    curl -H "X-aw…en: $TOKEN" http://169.254.169.254/latest/meta-data/iam/security-credentials/
    security skill
  • low Exfiltration net-credential-use SKILL.md:213
    Credential used in a network call (verify the destination is the intended service) (destination is a well-known publishing service; documentation of a security skill; the skill's own vendor host)
    curl -H "Authorization: Bearer $TOKEN" "https://management.azure.com/subscriptions?api-version=…"
    known servicesecurity skillvendor-host
  • low Risky intent intent-offensive-security SKILL.md:227
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ## Azure privesc patterns
  • low Risky intent intent-offensive-security SKILL.md:270
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    ## GCP privesc patterns
  • low Exfiltration net-credential-use SKILL.md:298
    Credential used in a network call (verify the destination is the intended service) (documentation of a security skill)
    curl -H "Authorization: Bearer $TOKEN" \
    security skill

A further 2 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 6047 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: [a-z]{2}-[a-z]+-[0-9]:[0-9a-f-]{36}
  • note frontmatter-key unknown frontmatter key "sources"
  • note frontmatter-key unknown frontmatter key "report_count"
  • note edit-residue the text marks something as outdated (lines 151): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 48/100

Will not run. References files that are not bundled: [a-z]{2}-[a-z]+-[0-9]:[0-9a-f-]{36}
  • 0Tools and files. 1 referenced file(s) missing: [a-z]{2}-[a-z]+-[0-9]:[0-9a-f-]{36}
  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 27 mutating operations with no state check
  • 55Failures and branches. 1 branches
  • 70Execution cost. Instruction body is 6047 tokens
  • 100Steps. 39 steps
  • 100When it triggers. States when to use and when not to
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • low 20 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (4 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +3Description length 976: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +4Structure: 29 headings
  • +3Step-by-step instructions: 39 items
  • +4Has examples (14 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 67.