ClawAudit verdict
memory-system
memory-system-pro-v2
The skill accesses credentials and has potential security risks.
⚠ 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
agent_memory
Findings (5)
References agent memory files
SKILL.md · code · MEMORY.md
Uses exec() — may execute shell commands
src/autoDream.ts · prose · downgraded · exec(
References child_process — can spawn system processes
src/embed.ts · prose · downgraded · child_process
Dynamic import() — loads module at runtime
src/flush.ts · prose · downgraded · import('
Accesses sensitive environment variables
src/autoDream.ts · prose · downgraded · process.env.MINIMAX_CODING_API_KEY
Permissions & capabilities
No declared permissions — minimal attack surface.
agent_memorycredential_access Is this flag fair?
Thanks — recorded.