ClawAudit verdict

code-security-auditor

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Reads local files AND makes external network calls

Code security audit skill running local SAST scans with standard tools (pip-audit, npm audit, trufflehog, gitleaks); all operations are local analysis with no evidence of sending scan results or source code to external hosts.

Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

0
security
40
transparency
70
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but ClawAudit detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination critical

Reads local files AND makes external network calls — the capabilities for data exfiltration co-occur (data-flow not verified)

LLM02 · LLM06 · ASI03

Capability combination high

Accesses credentials AND makes external network calls — potential credential theft

LLM02 · ASI03

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Performs file operations but does not declare file-accessing binaries

file_read

Code accesses API keys/tokens but declares no environment variables

credential_access

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (14)

Pattern match critical

Pipe to python — executes piped content as Python code

references/owasp-top10.md · code · | python

Pattern match high

subprocess execution — runs system commands from Python

references/owasp-top10.md · code · subprocess.run(

Pattern match high

os.system/popen — direct OS command execution

references/owasp-top10.md · code · os.system(

Pattern match high

Uses eval() — can execute arbitrary code

rules/extended-rules.md · prose · downgraded · eval(

Pattern match high

Accesses sensitive system files

rules/extended-rules.md · prose · downgraded · /etc/passwd

Pattern match high

Possible hardcoded credential

test_vulnerable.py · prose · downgraded · API_KEY = "sk-1234567890abcdefghijklmnopqrstuvwxyz

Pattern match medium

Python urllib.request — network access

SKILL.md · code · urllib.request

Pattern match medium

Sets world-executable permissions

SKILL.md · code · chmod 755

Pattern match medium

Uses exec() — may execute shell commands

rules/extended-rules.md · prose · downgraded · exec(

Pattern match medium

subprocess with shell=True — command injection vector

rules/extended-rules.md · prose · downgraded · subprocess.call(var, shell=True

Pattern match medium

Gopher protocol — SSRF attack vector

rules/extended-rules.md · prose · downgraded · gopher://

Pattern match low

Popular HTTP library — network access

auditor.py · prose · downgraded · axios

Pattern match low

Python os.environ.get — reads environment variable

auditor.py · prose · downgraded · os.environ.get(

Pattern match low

Opens WebSocket connection

rules/extended-rules.md · prose · downgraded · WebSocket

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

credential_accessnetwork_outfile_readnetwork_inpackage_install
Check another skill Browse the registry Auditing your own skills or configs? Use the API