ClawAudit verdict
emoclaw
Local emotion modeling skill that trains a small neural net on agent identity files and injects emotional state into the system prompt; Claude API usage during bootstrap is explicitly opt-in and clearly disclosed.
⚠ 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 (6)
Uses eval() — can execute arbitrary code
engine/emotion_model/tests/test_model.py · prose · downgraded · eval(
Base64 encoding/decoding
references/architecture.md · code · base64-encode
subprocess execution — runs system commands from Python
scripts/bootstrap.py · prose · downgraded · subprocess.run(
References agent memory files
assets/emoclaw.yaml · prose · downgraded · MEMORY.md
Python os.environ.get — reads environment variable
engine/emotion_model/config.py · prose · downgraded · os.environ.get(
Python shutil file operation — copies/moves/deletes files
scripts/setup.py · prose · downgraded · shutil.copytree(
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.
package_installdata_encoding Is this flag fair?
Thanks — recorded.