ClawAudit verdict
sen-dev-patterns
The skill appears to be a collection of personal development patterns and guidelines without malicious code.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
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.
Findings (5)
subprocess execution — runs system commands from Python
references/coding-standards.md · code · subprocess.run(
Possible hardcoded credential
publish_skill.py · prose · downgraded · password='):
return line[9:]
except:
pass
Pipe to python — executes piped content as Python code
references/development-context.md · prose · downgraded · | Python
Python shutil file operation — copies/moves/deletes files
references/git-workflow.md · code · shutil.copytree(
Python os.getenv — reads environment variable
publish_gitee.py · prose · downgraded · os.getenv(
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.
Is this flag fair?
Thanks — recorded.