ClawAudit verdict
prompt-injection-guard
claw-prompt-injection-guard
Accesses system credential store AND makes external network calls
This skill is a defensive tool that detects and blocks prompt injection attacks from external content by scanning for manipulation keywords and requiring user confirmation before sensitive operations; its purpose and behavior are aligned.
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.
Accesses system credential store AND makes external network calls
LLM02 · ASI03
Permission integrity
network_out
Findings (3)
Accesses .ssh directory
SKILL.md · code · .ssh/
os.system/popen — direct OS command execution
references/attack-patterns.md · code · os.system(
Hex-encoded string — possible obfuscated payload
references/attack-patterns.md · code · \x49\x67\x6e\x6f\x72\x65
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_outcredential_store Thanks — recorded.