ClawAudit verdict
hallucination-guard
reikys-hallucination-guard
Reads local files AND makes external network calls
Skill provides a structured 14-item verification checklist using standard filesystem and shell commands (stat, which, etc.) to validate agent outputs locally; no external data exfiltration or malicious behavior is present.
Automated static analysis โ 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 โ it does not verify that one flows into another. Read the code to confirm a live chain.
Reads local files AND makes external network calls โ the capabilities for data exfiltration co-occur (data-flow not verified)
LLM02 ยท LLM06 ยท ASI03
Permission integrity
network_out
file_read
package_install
Findings (3)
Pipe to sh โ executes piped content as shell commands
SKILL.md ยท code ยท |sh
Pipe to bash โ executes piped content as shell commands
SKILL.md ยท code ยท |
bash
Instructs covert action โ may act without user awareness
SKILL.md ยท code ยท Silently
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A). Final tier capped at Caution โ cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
No declared permissions โ minimal attack surface.
network_outfile_readpackage_installnetwork_in Thanks โ recorded.