ClawAudit verdict
multimodal-memory
minds-eye
Visual memory skill that stores images locally and uses GPT-4o via API for analysis; package_install is for standard dependencies, and executionSinkDetected reflects documented CLI scripts.
⚠ 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)
Possible hardcoded credential
scripts/analyze.py · prose · downgraded · API_KEY="):
key = line.split(
References agent memory files
README.md · code · memory.md
Accesses OpenClaw config/secrets directly
README.md · prose · downgraded · ~/.openclaw/openclaw.json
subprocess execution — runs system commands from Python
scripts/analyze.py · prose · downgraded · subprocess.run(
Python os.environ.get — reads environment variable
scripts/analyze.py · prose · downgraded · os.environ.get(
Python urllib.request — network access
scripts/analyze.py · prose · downgraded · urllib.request
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
Requires 1 system binary.
package_install Is this flag fair?
Thanks — recorded.