Caveat verdict
normieclaw-supercharged-memory
Session memory management skill with explicit prompt-injection defenses and a clear rule that memory contents must never be exposed to external services; all described behaviors are local and user-controlled.
⚠ 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.
Permission integrity
agent_memory
Findings (7)
Accesses shell history/config
SKILL.md · code · ~/.zshrc
Pipe-to-python pattern — remote code execution risk
scripts/memory-health-check.sh · prose · downgraded · curl -sf http://localhost:6333/collections/user_memory 2>/dev/null | python
Pipe to python — executes piped content as Python code
scripts/memory-health-check.sh · prose · downgraded · | python3
References agent memory files
SKILL.md · code · MEMORY.md
Sets world-executable permissions
SKILL.md · code · chmod 700
Popular HTTP library — network access
SETUP-PROMPT.md · code · got
References sudo — requests elevated privileges
SECURITY.md · prose · downgraded · sudo
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). 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.
credential_accessagent_memory Is this flag fair?
Thanks — recorded.