ClawAudit verdict
bettafish-opinion-analysis
Multi-agent social media sentiment analysis framework that fetches public data via WebSearch/WebFetch/Browser and generates local HTML/Word/PDF reports; data flow is transparent and consistent with the stated analysis purpose.
⚠ 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
network_out
Findings (6)
Pipe-to-python pattern — remote code execution risk
SKILL.md · code · curl -s "https://api.example.com/data" | python
Pipe to python — executes piped content as Python code
SKILL.md · code · | python
<script> tag in markdown — potential code injection
references/design_guide.md · code · <script>
subprocess execution — runs system commands from Python
subskills/docx/scripts/accept_changes.py · prose · downgraded · subprocess.run(
Python shutil file operation — copies/moves/deletes files
subskills/docx/scripts/comment.py · prose · downgraded · shutil.copy(
Popular HTTP library — network access
subskills/pdf/scripts/fill_fillable_fields.py · prose · downgraded · got
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class C/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.
network_out Is this flag fair?
Thanks — recorded.