Caveat verdict
huo15-memory-evolution
A local memory management system for OpenClaw agents that reads/writes markdown files and uses a Dream Agent for LLM-driven log summarization; agent_memory capability matches the stated memory evolution purpose.
⚠ 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 (6)
Pipe to python — executes piped content as Python code
scripts/context-suggest.sh · prose · downgraded · | python3
Possible hardcoded credential
scripts/dream-api.py · prose · downgraded · API_KEY = "sk-cp-pD1WY6KcHeUNXDeKmG4ZnzDch-sXsZKmAsNn7rXZDoAbGwc7u6XJn55Z6GbgW3q
References agent memory files
SKILL.md · code · MEMORY.md
os.system/popen — direct OS command execution
scripts/dream-api.py · prose · downgraded · os.system(
References agent configuration files
SKILL.md · prose · downgraded · CLAUDE.md
Python urllib.request — network access
scripts/dream-api.py · prose · downgraded · urllib.request
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.
agent_memory Is this flag fair?
Thanks — recorded.