ClawAudit verdict
adam-framework
The skill contains executionSinkDetected=true, which indicates potential malicious behavior.
⚠ 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.
Findings (10)
Instructs covert action — may act without user awareness
docs/CONTEXT_COMPILER.md · code · Silently
References agent memory files
AGENTS.md · code · MEMORY.md
Accesses OpenClaw config/secrets directly
docs/LESSONS_LEARNED.md · prose · downgraded · ~/.openclaw/openclaw.json
References sudo — requests elevated privileges
docs/SETUP.md · prose · downgraded · sudo
subprocess execution — runs system commands from Python
tools/update_live_stats.py · prose · downgraded · subprocess.run(
Possible prompt injection — attempts to redefine agent identity
vault-templates/SOUL.template.md · prose · downgraded · You are now
Popular HTTP library — network access
SKILL.md · prose · downgraded · got
Python os.environ.get — reads environment variable
mcp-server/server.py · prose · downgraded · os.environ.get(
References agent configuration files
README.md · prose · downgraded · CLAUDE.md
Python shutil file operation — copies/moves/deletes files
tools/test_coherence_monitor.py · prose · downgraded · shutil.rmtree(
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.
Is this flag fair?
Thanks — recorded.