ClawAudit verdict
code-sandbox
Fetches from network AND uses eval/Function
Code sandbox skill that defines isolation policies (resource limits, network blocking, filesystem restrictions) for safely executing AI-generated code; the skill describes a security framework rather than performing exfiltration.
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.
What it does
These are capability combinations: each listed behavior occurs in the skill, but ClawAudit 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 (3)
Recursive delete from root or home — destructive command
SKILL.md · code · rm -rf /
References child_process — can spawn system processes
SKILL.md · code · child_process
os.system/popen — direct OS command execution
SKILL.md · code · os.system(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class 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.
network_outfile_readprocess_execdynamic_eval Thanks — recorded.