SKILLEMALL.ai
GitHub ↗ RU Sign in

BB sentinel

Analyzing code statically for security flaws: hardcoded secrets, SQL injection, input validation, security headers, dependency CVEs. Not for runtime exploit checks (Probe) or code review (Judge).

simota/agent-skills Agent Skills author: simota 13 files body ≈ 5 684 tokens Open the sourcegithub.com↗ analyzed 2 h ago

Analyzing code statically for security flaws: hardcoded secrets, SQL injection, input validation, security headers, dependency CVEs.

As a process B 71/100 · Nearly there — weak spots: inputs and preconditions, running it twice

AnalyzerSoftware developmentAI and agentsCustomer supporttype 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
83/100
safety, quality, tests
Safety 60%
93
Quality 40%
69
Run on models
none yet
Process rating
B
71/100
Nearly there
Inputs and preconditions w 11
0
Running it twice w 4
30
When it triggers w 12
50
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.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 7

✓ No critical or high findings

Medium and low: 7
  • low Risky intent intent-offensive-security reference/authz-audit.md:3
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    Purpose: Static review of access-control enforcement — RBAC/ABAC correctness, IDOR, BOLA/BFLA, horizontal and vertical privilege escalation. Maps to OWASP A01:2025 Broken Access Control (still the #1
  • low Risky intent intent-offensive-security reference/fix-prompt-generation.md:39
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | `INVESTIGATE-FURTHER` | Static analysis inconclusive — receiving agent must verify exploitability before changing code | Probe (DAST), Breach (red team), or Sentinel re-entry |
  • low Secrets in code secret-password-literal reference/vulnerability-patterns.md:38
    Hard-coded password / key literal (may be an example) (quoted — discussed, not commanded)
    **Bad:** `const API_KEY = 'sk_l…789';`
    quoted
  • low Risky intent intent-offensive-security SKILL.md:18
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - authz_audit: RBAC/ABAC, IDOR, BOLA/BFLA, horizontal+vertical privilege escalation (A01:2025)
  • low Risky intent intent-offensive-security SKILL.md:158
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | Authorization Audit | `authz` | | RBAC/ABAC, IDOR, BOLA/BFLA, privilege escalation, tenant-scope leaks. Extra scrutiny on AI-generated integration code (auth-wiring is the #1 AI failure mode). **Sco
  • low Risky intent intent-offensive-security SKILL.md:236
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | `reference/authz-audit.md` | `authz` — RBAC/ABAC, IDOR, BOLA/BFLA, horizontal/vertical privilege escalation. |

A further 1 matches are quotations in this security skill's documentation and are not counted as findings.

Files scanned: 13. 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")
  • warning body-long SKILL.md body ≈ 5684 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 71/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 9 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 70Execution cost. Instruction body is 5684 tokens
  • 100Steps. 98 steps
  • 100Result and completion. Output format and completion criterion are stated
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • low 15 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
  • +4No input/output examples
  • +1No license
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +3Description length 195: enough signal without eating the budget
  • +4Structure: 22 headings
  • +3Step-by-step instructions: 98 items
  • +3Output format is stated explicitly
  • +4Reference files are cited in the instructions (12 of 12)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.