BC code-security-auditor
Comprehensive code security audit with AI-powered vulnerability detection. Covers OWASP Top 10, dependency scanning, secret detection, SAST, and provides actionable fix recommendations. Use when security review, penetration testing, or compliance audit is needed.
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- 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
-
medium Exfiltration
net-redirectable-api-keyllm_integration.py:39Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
-
low Risky intent
intent-offensive-securityREADME.md:16Offensive-security / dual-use content (legitimate for authorised testing; review intended use)| **SAST 静态分析** | 代码流分析、污点追踪 | pentest/security-reviewer |
-
low Risky intent
intent-offensive-securityREADME.md:224Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- [pentest/security-reviewer](https://clawhub.com) - SAST 分析
-
low Risky intent
intent-offensive-securityreferences/owasp-top10.md:17Offensive-security / dual-use content (legitimate for authorised testing; review intended use)### 3. pentest/security-reviewer (ClawHub)
-
low Dangerous commands
cmd-eval-dynamicreferences/owasp-top10.md:89Dynamic code execution from decoded/untrusted input (documentation of a security skill)os.system(f"ping {user_input}")security skill -
low Risky intent
intent-offensive-securitySKILL.md:3Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)description: Comprehensive code security audit with AI-powered vulnerability detection. Covers OWASP Top 10, dependency scanning, secret detection, SAST, and provides actionable fix recommendations. U
detector -
low Secrets in code
secret-labelled-tokentest_vulnerable.py:22Labelled token / key literal (vendor format unknown — verify it is not a live credential) (placeholder value)API_KEY = "sk-1…xyz"
placeholder -
low Secrets in code
secret-password-literaltest_vulnerable.py:22Hard-coded password / key literal (may be an example) (placeholder value)API_KEY = "sk-1…xyz"
placeholder -
low Secrets in code
secret-aws-keytest_vulnerable.py:23AWS access key ID (placeholder value)AWS_ACCESS_KEY = "AKIA…PLE"
placeholder -
low Dangerous commands
cmd-eval-dynamictest_vulnerable.py:40Dynamic code execution from decoded/untrusted input (test fixture / example file; documentation of a security skill)os.system(f"ping -c 4 {host}")fixturesecurity skill
A further 2 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 19. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 53/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 100Tools and files. No external tools needed
- 100Steps. 33 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3613 tokens
- 100Running it twice. No mutating operations
- 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)
- +3Output format is not stated: the model decides each time
- -243 emoji in the instructions: noise for the model
- -43 reference files, but SKILL.md never points to them: the model will not open them
- +1No license
- +2Single-language instructions
- +3Description length 263: enough signal without eating the budget
- +4Structure: 43 headings
- +3Step-by-step instructions: 33 items
- +4Has examples (28 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.