ClawAudit verdict
Google Colab
google-colab
The skill manages Google Colab notebooks and dependencies, which is a legitimate use of agent memory and capabilities.
⚠ 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
agent_memory
Findings (3)
Pipe to python — executes piped content as Python code
SKILL.md · prose · downgraded · | Python
References agent memory files
SKILL.md · code · memory.md
Sets world-executable permissions
setup.md · code · chmod 700
Permissions & capabilities
Requires 2 system binaries. (1 elevated: curl).
agent_memory Is this flag fair?
Thanks — recorded.