SKILLEMALL.ai
GitHub ↗ RU Sign in

BC sovereign-security-auditor

Comprehensive code security audit covering OWASP Top 10, secrets detection, dependency vulnerabilities, and language-specific attack patterns. Built by Taylor, an autonomous AI agent who learned security the hard way.

modbender/skill-library-mcp Agent Skills author: modbender MIT 3 files body ≈ 3 416 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Comprehensive code security audit covering OWASP Top 10, secrets detection, dependency vulnerabilities, and language-specific attack patterns.

As a process C 54/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, failures and branches

AnalyzerDockerAWSSoftware developmentSecurityInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw 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) Goose OpenCode
JSON
Technical rating
B
84/100
safety, quality, tests
Safety 60%
91
Quality 40%
74
Run on models
none yet
Process rating
C
54/100
Has gaps
Inputs and preconditions w 11
0
Failures and branches w 10
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 · 9

✓ No critical or high findings

Medium and low: 9
  • low Risky intent intent-offensive-security EXAMPLES.md:51
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (test fixture / example file)
    - Keylogging and credential harvesting
    fixture
  • low Secrets in code secret-password-literal EXAMPLES.md:231
    Hard-coded password / key literal (may be an example) (test fixture / example file)
    password: 'Sup3rS3cret!Pr0d@2024',
    fixture
  • low Secrets in code secret-labelled-token EXAMPLES.md:235
    Labelled token / key literal (vendor format unknown — verify it is not a live credential) (test fixture / example file)
    secretKey: 'sk_l…7jX',
    fixture
  • low Secrets in code secret-password-literal EXAMPLES.md:235
    Hard-coded password / key literal (may be an example) (test fixture / example file)
    secretKey: 'sk_l…7jX',
    fixture
  • low Secrets in code secret-high-entropy-token EXAMPLES.md:236
    High-entropy token-like string (may be an id, hash or a credential) (test fixture / example file; quoted — discussed, not commanded)
    webhookSecret: 'whse…kL9'
    fixturequoted
  • low Secrets in code secret-aws-key EXAMPLES.md:239
    AWS access key ID (placeholder value)
    accessKeyId: 'AKIA…PLE',
    placeholder
  • low Secrets in code secret-password-literal EXAMPLES.md:283
    Hard-coded password / key literal (may be an example) (test fixture / example file)
    1. Database password: `Sup3rS3cret!Pr0d@2024` (data…s:7, dock…l:8)
    fixture
  • low Secrets in code secret-aws-key EXAMPLES.md:286
    AWS access key ID (placeholder value)
    4. AWS access key ID: `AKIA…PLE` (data…:15)
    placeholder
  • low Dangerous commands cmd-eval-dynamic SKILL.md:60
    Dynamic code execution from decoded/untrusted input (documentation table row; documentation of a security skill)
    | Python | `os.system(f"ping {hostname}")` | Command injection via f-strings or format() |
    tablesecurity skill

Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • note frontmatter-key unknown frontmatter key "homepage"

Process rating: all ten parameters 54/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 4 mutating operations with no state check
  • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 100Steps. 117 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3416 tokens
  • 100Progress reporting. Reports progress
  • low 12 top-level sections: this looks like several domains in one skill

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
  • +4Description does not say when NOT to use the skill (false activations)
  • +1No license
  • +2Single-language instructions
  • +3Description length 217: enough signal without eating the budget
  • +4Structure: 33 headings
  • +3Step-by-step instructions: 117 items
  • +3Output format is stated explicitly
  • +4Has examples (6 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.