Caveat verdict

anima-aios

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

AI agent cognitive memory system providing 5-layer memory architecture with local storage and optional watchdog monitoring; background behavior is disclosed and opt-in.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

Automated static analysis — not a human review. Caveat flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

58
security
70
transparency
70
maintenance

Permission integrity

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (9)

Pattern match medium

Uses exec() — may execute shell commands

core/session_scanner.py · prose · downgraded · exec(

Pattern match medium

References sudo — requests elevated privileges

hooks/README.md · prose · downgraded · sudo

Pattern match low

Python os.getenv — reads environment variable

anima_doctor.py · prose · downgraded · os.getenv(

Pattern match low

References agent configuration files

config/config_loader.py · prose · downgraded · agent_config

Pattern match low

References agent memory files

core/dimension_calculator.py · prose · downgraded · MEMORY.md

Pattern match low

Python urllib.request — network access

core/distill_engine.py · prose · downgraded · urllib.request

Pattern match low

Python shutil file operation — copies/moves/deletes files

core/native_importer.py · prose · downgraded · shutil.copytree(

Pattern match low

Popular HTTP library — network access

core/self_reflection.py · prose · downgraded · got

Pattern match low

pip3 install — installs Python packages at runtime

post-install.sh · prose · downgraded · pip3 install

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B/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.

package_installnetwork_in

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API