no-ai-slop
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructions for the agent to act as a human editor. It contains no executable scripts, shell commands, or network-enabled tools. The external link provided in the source documentation points to a well-known code repository for informational purposes only.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied drafts, which represent a potential surface for indirect prompt injection. However, since the skill has no access to sensitive system tools or network capabilities, the risk is limited to potential output distortion.\n
- Ingestion points: User-provided drafts submitted for editing or analysis as described in
SKILL.md.\n - Boundary markers: Not present; user input is processed as raw text without isolation markers.\n
- Capability inventory: Limited to text generation and analysis; no file system, network, or subprocess capabilities are utilized.\n
- Sanitization: No explicit sanitization of input is performed, but the evaluation steps in
eval.mdprovide a procedural check to ensure the output remains focused on the user's original point.
Audit Metadata