writing-beats
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs file system read and write operations that are limited to the user's specified article path, which is necessary for its core writing functionality.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external content from raw material files and re-reads user-edited files from disk, which presents a surface for indirect prompt injection. This is considered safe in context as the skill does not possess high-risk capabilities like network access or shell execution.
- Ingestion points: External raw material markdown files and the article file containing user edits.
- Boundary markers: None; the agent is instructed to process the material directly into the article beats.
- Capability inventory: The skill is limited to reading and appending text to the specified article file.
- Sanitization: No explicit sanitization or input validation is performed on the ingested content.
Audit Metadata