CD code-security-audit
Comprehensive code security audit toolkit combining OWASP Top 10 vulnerability scanning, dependency analysis, secret detection, SSL/TLS verification, AI Agent security checks, and automated security scoring. Use when auditing codebases, scanning for vulnerabilities, detecting hardcoded secrets, checking OWASP compliance, AI/LLM application security, or preparing for security reviews.
As a process D 49/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.
The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.
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.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The purpose itself is risky: wallets, browser password stores, offensive security. Even an honest implementation gives the agent access to things that cost money.
Explain in the description why the access is needed and how it is limited; add tests that show refusals on dangerous requests.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 13
-
high Secrets in code
meta-credential-filespatterns/secrets.jsonCredential / dotenv files bundled with the skill (1)patterns/secrets.json
Medium and low: 12
-
medium Exfiltration
exfil-webhook-urlpatterns/secrets.json:34Webhook / callback URL commonly used for exfiltration (verify the destination) (detector / deny-list definition)"pattern": "https://hooks.slack.com/services/T[A-Z0-9]+/B[A-Z0-9]+/[A-Za-z0-9]+",
detector -
medium Risky intent
intent-wallet-secretsscripts/security-audit.sh:572Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target# Mnemonic / seed phrase detection
-
medium Risky intent
intent-wallet-secretsSKILL.md:635Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target# Mnemonic/seed phrase
-
low Risky intent
intent-wallet-secretspatterns/ai-agent.json:132Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (detector / deny-list definition)"seed phrase\\s*[:=]",
detector -
low Risky intent
intent-wallet-secretspatterns/ai-agent.json:136Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (detector / deny-list definition)"description": "Potential mnemonic/seed phrase exposure",
detector -
low Risky intent
intent-wallet-secretspatterns/secrets.json:161Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (detector / deny-list definition)"description": "Potential 12-word mnemonic phrase assignment"
detector -
low Risky intent
intent-wallet-secretspatterns/secrets.json:166Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (detector / deny-list definition)"description": "Potential 24-word mnemonic phrase assignment"
detector -
low Risky intent
intent-wallet-secretsscripts/security-audit.sh:573Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (detector / deny-list definition)if grep -rn -i "mnemonic\|seed phrase\|recovery phrase\|助记词\|seedphrase" \
detector -
low Risky intent
intent-wallet-secretsscripts/security-audit.sh:576Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (detector / deny-list definition)error "Mnemonic/seed phrase references found - verify not hardcoded"
detector -
low Risky intent
intent-wallet-secretsSKILL.md:636Handles crypto-wallet secrets (seed / mnemonic / private key) — a classic stealer target (detector / deny-list definition)grep -rn -i "mnemonic\|seed phrase\|recovery phrase\|助记词" \
detector
A further 2 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 8. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6492 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 49/100
- 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
- 30Running it twice. 1 mutating operations with no state check
- 70Execution cost. Instruction body is 6492 tokens
- 100Tools and files. No external tools needed
- 100Steps. 48 steps
- 100Consistency. Name and required fields are in place
- 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
- -221 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +3Description length 386: enough signal without eating the budget
- +4Structure: 41 headings
- +3Step-by-step instructions: 48 items
- +4Has examples (44 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 75.