ClawAudit verdict
recursive-maths-animator
skill appears to be for generating mathematical animations, uses Manim, and has a brief-first workflow
⚠ 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 (6)
References sudo — requests elevated privileges
references/manim_guide.md · code · sudo
subprocess execution — runs system commands from Python
references/design_systems/font_catalog.py · prose · downgraded · subprocess.run(
Python os.environ.get — reads environment variable
references/manim_guide.md · code · os.environ.get(
conda install — installs packages via conda
references/manim_guide.md · code · conda install
Python shutil file operation — copies/moves/deletes files
references/manim_versioning.py · prose · downgraded · shutil.copy(
importlib.import_module — dynamic module loading
scripts/check_environment.py · prose · downgraded · importlib.import_module(
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.
agent_memory Is this flag fair?
Thanks — recorded.