ClawAudit verdict
fund-ai-assistant
A local-first fund portfolio analysis tool fetching public market data and using a user-configured LLM API key; the skill explicitly warns about using a dedicated API key and discloses security implications of custom LLM_API_BASE endpoints.
⚠ 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.
Permission integrity
file_read+write
package_install
Findings (6)
Possible hardcoded credential
SKILL.md · code · API_KEY="tvly-xxx
Pipe to python — executes piped content as Python code
SKILL.md · prose · downgraded · | python3
References webhook/callback URL
SKILL.md · code · WEBHOOK_URL
Python os.environ.get — reads environment variable
ai_analysis.py · prose · downgraded · os.environ.get(
pip3 install — installs Python packages at runtime
correlation.py · prose · downgraded · pip3 install
Python urllib.request — network access
event_monitor.py · prose · downgraded · urllib.request
Permissions & capabilities
No declared permissions — minimal attack surface.
network_inpackage_installfile_write Is this flag fair?
Thanks — recorded.