debloat
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external text which could potentially contain malicious instructions designed to subvert the agent's logic. While this is an inherent risk of processing untrusted content, the skill instructions are focused on structural and stylistic edits. \n
- Ingestion points: Supplied prose files referenced in SKILL.md. \n
- Boundary markers: None specified in the instructions to delimit the input text. \n
- Capability inventory: The skill requires file-write access to edit prose in place and potential network access for link verification. \n
- Sanitization: No specific sanitization or filtering of the input content is mentioned.
Audit Metadata