Caveat verdict
clawmem-setup
clawmem
Fetches from network AND uses eval/Function
The skill is a setup/bootstrap guide for a memory plugin that installs via the standard openclaw plugin system and reads config files; the dynamic_eval capability reflects Python inline config inspection, which matches the stated purpose of verifying plugin provisioning.
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.
What it does
These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Fetches from network AND uses eval/Function — the remote-code-execution pattern (data-flow not verified)
LLM05 · LLM06 · ASI05
Reads files AND uses eval/Function — may execute locally stored payloads
LLM05 · LLM06 · ASI05
Reads local files AND makes external network calls — the capabilities for data exfiltration co-occur (data-flow not verified)
LLM02 · LLM06 · ASI03
Executes processes AND makes external network calls — may exfiltrate command output
LLM02 · LLM06 · ASI03
Permission integrity
network_out
Findings (2)
Possible hardcoded credential
SKILL.md · code · TOKEN="$CLAWMEM_TOKEN
subprocess execution — runs system commands from Python
SKILL.md · code · subprocess.check_output(
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.
file_readprocess_execdynamic_evalcredential_accessnetwork_out Thanks — recorded.