ClawAudit verdict
paper2poster
newpaper-skill
The skill clones a GitHub repository, installs dependencies, and executes commands. While the intent seems legitimate, the use of dynamic_eval and package_install capabilities raises concerns about potential security risks.
⚠ 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
package_install
Findings (3)
References sudo — requests elevated privileges
README.md · code · sudo
conda install — installs packages via conda
README.md · code · conda install
References agent configuration files
README.md · prose · downgraded · agent_config
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). 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.
dynamic_evalpackage_install Is this flag fair?
Thanks — recorded.