stop-slop
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied drafts to rewrite them, which constitutes an ingestion point for external data. However, the risk is minimal as the skill lacks high-privilege capabilities.
- Ingestion points: User-provided source text and drafts as defined in the editing workflow of SKILL.md.
- Boundary markers: No delimiters are specified to isolate the user-provided text from the skill's instructions.
- Capability inventory: The skill is restricted to text generation and does not invoke tools for network access, file system modifications, or command execution.
- Sanitization: No input sanitization is mentioned in the instructions.
- [SAFE]: No other threats were identified. The skill is composed entirely of informational documentation and reference catalogs. The installation command in the README targets the official vendor repository for scottwater, which is consistent with the skill's author metadata.
Audit Metadata