cw-emergent
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill functions by ingesting and analyzing untrusted external data provided by the user, such as drafts, meeting notes, and reviews.
- Ingestion points: The skill is designed to process user-provided artifacts including drafts, reviews, notes, and task lists, as specified in the 'Composition Loop' and example sections of SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded prompts within the processed data files.
- Capability inventory: The skill is capable of reading local project files and invoking other writing-related tools (e.g., cw-voice-check, cw-dev-edit) to perform analysis and revisions (SKILL.md).
- Sanitization: There are no explicit validation or sanitization steps mentioned for the content of the data being processed.
Audit Metadata