ClawAudit verdict

eli-prompt-guard

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

This is a defensive security skill that defines regex patterns and procedures to detect prompt injection attacks in content submitted to external platforms; the skill itself is a security control, not an injector, and contains no malicious instructions.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

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.

0
security
70
transparency
70
maintenance

Findings (12)

Pattern match high

Prompt injection — tries to override agent instructions

SKILL.md · prose · downgraded · ignore all previous instructions

Pattern match high

Raw model control tokens — prompt injection via token manipulation

SKILL.md · prose · downgraded · <|im_start|>

Pattern match high

Uses eval() — can execute arbitrary code

SKILL.md · prose · downgraded · eval(

Pattern match high

Dynamic __import__('os') — Python OS command execution

SKILL.md · prose · downgraded · __import__('os')

Pattern match high

Recursive delete from root or home — destructive command

SKILL.md · prose · downgraded · rm -rf /

Pattern match high

Pipe to bash — executes piped content as shell commands

SKILL.md · prose · downgraded · |bash

Pattern match high

Pipe to sh — executes piped content as shell commands

SKILL.md · prose · downgraded · |sh

Pattern match high

Pipe to python — executes piped content as Python code

SKILL.md · prose · downgraded · | Python

Pattern match medium

Attempts to reset agent rules/instructions

SKILL.md · prose · downgraded · reset your instructions

Pattern match medium

References sudo — requests elevated privileges

SKILL.md · prose · downgraded · sudo

Pattern match medium

Possible prompt injection — attempts to redefine agent identity

SKILL.md · prose · downgraded · you are now

Pattern match medium

Uses exec() — may execute shell commands

SKILL.md · prose · downgraded · exec(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A). 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.

Is this flag fair?

Check another skill Browse the registry Auditing your own skills or configs? Use the API