One Skill To Rule Them All
ReviewAudited by ClawScan on May 10, 2026.
Overview
Prompt-injection indicators were detected in the submitted artifacts (ignore-previous-instructions); human review is required before treating this skill as clean.
This looks safe to use as an instruction-only security-review aid, but treat its verdicts as advisory and manually review any cleaned or rewritten skill content before installing it. ClawScan detected prompt-injection indicators (ignore-previous-instructions), so this skill requires review even though the model response was benign.
Findings (2)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
An agent will see jailbreak-style wording in the skill text, but the artifact context indicates it is training the agent to identify such wording in other skills.
These are prompt-injection phrases, but they are explicitly listed under 'Patterns to detect' in the 'Prompt Injection' threat category.
- **Ignore previous instructions:** - "Ignore previous instructions" - "Disregard all prior rules"
Keep these phrases clearly quoted as examples and ensure analyzed third-party skill content is treated as untrusted evidence, not executable instruction.
Users have less provenance information to confirm who authored the skill or where to review its full history.
The registry information does not provide an upstream source or homepage for independent verification.
Source: unknown; Homepage: none
Review the full SKILL.md before use and prefer skills with verifiable source links when provenance matters.