BF security-pen-testing
Use when the user asks to perform security audits, penetration testing, vulnerability scanning, OWASP Top 10 checks, or offensive security assessments. Covers static analysis, dependency scanning, secret detection, API security testing, and pen test report generation.
Covers static analysis, dependency scanning, secret detection, API security testing, and pen test report generation.
As a process F 51/100 · Will not run — References files that are not bundled: ../senior-secops/SKILL.md, ../senior-security/SKILL.md, engineering/skills/dependency-auditor/SKILL.md
How to improve
- 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 · 14
✓ No critical or high findings
Medium and low: 14
-
low Obfuscation
obf-hex-escape-chainreferences/attack_patterns.md:30Escaped/char-code string obfuscation (documentation of a security skill)<script>alert(String.fromCharCode(100,111,99,117,109,101,110,116,46,100,111,109,97,105,110))</script>
security skill -
low Secrets in code
secret-high-entropy-tokenreferences/attack_patterns.md:202High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)# Step 1: curl -H "X-aw…ds: 21600" -X PUT http://169.254.169.254/latest/api/token
quoted -
low Risky intent
intent-offensive-securityreferences/owasp_top_10_checklist.md:19Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| 1 | Horizontal privilege escalation | Change user ID in API requests (`/users/123` to `/users/124`) | 403 Forbidden |
-
low Risky intent
intent-offensive-securityreferences/owasp_top_10_checklist.md:20Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| 2 | Vertical privilege escalation | Access admin endpoints with regular user token | 403 Forbidden |
-
low Risky intent
intent-offensive-securityreferences/responsible_disclosure.md:214Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)1. **Written authorization is required.** For external testing, obtain a signed rules-of-engagement document or scope-of-work. For bug bounty programs, the program's terms of service serve as authoriz
detector -
low Risky intent
intent-offensive-securityreferences/responsible_disclosure.md:218Offensive-security / dual-use content (legitimate for authorised testing; review intended use)3. **Stay within scope.** If the bug bounty program says "*.example.com only," do not test anything outside that scope. If your pen test contract covers the web application, do not pivot to internal n
-
low Risky intent
intent-offensive-securityreferences/responsible_disclosure.md:244Offensive-security / dual-use content (legitimate for authorised testing; review intended use)## Bug Bounty Program Integration
-
low Risky intent
intent-offensive-securityreferences/responsible_disclosure.md:249Offensive-security / dual-use content (legitimate for authorised testing; review intended use)2. **Bug bounty platforms:** HackerOne, Bugcrowd, Intigriti, YesWeHack
-
low Risky intent
intent-offensive-securityreferences/responsible_disclosure.md:252Offensive-security / dual-use content (legitimate for authorised testing; review intended use)### Bug Bounty Best Practices
-
low Risky intent
intent-offensive-securitySKILL.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)description: "Use when the user asks to perform security audits, penetration testing, vulnerability scanning, OWASP Top 10 checks, or offensive security assessments. Covers static analysis, dependency
quoted -
low Risky intent
intent-offensive-securitySKILL.md:6Offensive-security / dual-use content (legitimate for authorised testing; review intended use)# Security Penetration Testing
-
low Risky intent
intent-offensive-securitySKILL.md:8Offensive-security / dual-use content (legitimate for authorised testing; review intended use)Hands-on offensive security testing skill for finding vulnerabilities before attackers do. This is NOT compliance checking (see senior-secops) or security policy writing (see senior-security) — this i
-
low Risky intent
intent-offensive-securitySKILL.md:34Offensive-security / dual-use content (legitimate for authorised testing; review intended use)This skill provides the methodology, checklists, and automation for **offensive security testing** — actively probing systems to discover exploitable vulnerabilities. It covers web applications, APIs,
-
low Risky intent
intent-offensive-securitySKILL.md:226Offensive-security / dual-use content (legitimate for authorised testing; review intended use)See [responsible_disclosure.md](references/responsible_disclosure.md) for full disclosure timelines (standard 90-day, accelerated 30-day, extended 120-day), communication templates, legal consideratio
Files scanned: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../senior-secops/SKILL.md - warning
missing-refreference to a missing file: ../senior-security/SKILL.md - warning
missing-refreference to a missing file: engineering/skills/dependency-auditor/SKILL.md - warning
missing-refreference to a missing file: ../code-reviewer/SKILL.md
Process rating: all ten parameters 51/100
Will not run. References files that are not bundled: ../senior-secops/SKILL.md, ../senior-security/SKILL.md, engineering/skills/dependency-auditor/SKILL.md
- 0Tools and files. 4 referenced file(s) missing: ../senior-secops/SKILL.md, ../senior-security/SKILL.md, engineering/skills/dependency-auditor/SKILL.md
- 0Result and completion. Does not say what the result is
- 0Failures and branches. Linear process with no failure handling
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 57 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3387 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 268: enough signal without eating the budget
- +4Structure: 27 headings
- +3Step-by-step instructions: 57 items
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.