Caveat verdict
tricore
Agent memory architecture framework using a CLI tool (memctl.py) for structured memory management; executionSinkDetected is for documented memctl commands, no data exfiltration.
⚠ 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.
Findings (4)
Pipe to bash — executes piped content as shell commands
cognitive-skills/planning-with-files_zh.md · frontmatter · |Bash
subprocess execution — runs system commands from Python
cognitive-skills/react-agent_zh.md · code · subprocess.run(
References agent memory files
SKILL.md · prose · downgraded · MEMORY.md
Python shutil file operation — copies/moves/deletes files
tools/memctl.py · prose · downgraded · shutil.move(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/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.