ce-noslop
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves a legitimate purpose for linguistic improvement and follows best practices for AI agent instructions. It includes strict boundaries to avoid modifying technical content like code blocks, identifiers, or links.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text or files, which is an inherent surface for indirect injection. However, the risk is safe due to the following factors:
- Ingestion points: Processes text or file paths provided by the user as described in SKILL.md.
- Boundary markers: Explicitly instructs the agent to never touch code blocks, quoted text, frontmatter, link targets, or identifiers, reducing the risk of executing embedded code or instructions.
- Capability inventory: Limited to text transformation; the skill does not use subprocess calls, network operations, or file-write capabilities beyond returning transformed text.
- Sanitization: The agent is constrained by a strict pattern catalog in references/patterns.md that focuses on linguistic refinement rather than instruction following.
Audit Metadata