prose-standard
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for editing user-supplied content such as documentation and comments. While this creates a surface for indirect prompt injection, the skill lacks any capabilities (like file writing or network access) to perform malicious actions based on such input.
- Ingestion points: User-provided prose, JSDoc, and internal comments within the repository.
- Boundary markers: The instructions do not define specific delimiters for separating input text from instructions.
- Capability inventory: No tools, filesystem access, or network operations are included or requested.
- Sanitization: No input validation or filtering is specified for the processed text.
- [NO_CODE]: The skill is purely instructional and does not include any scripts, binary files, or package dependencies.
Audit Metadata