writing-beats
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides clear instructional logic for a collaborative writing process. It interacts with the local filesystem to read raw material and write the generated article, which is consistent with its primary purpose. Access to files is mediated by user input and explicit path definitions.
- [PROMPT_INJECTION]: The skill ingests external markdown files provided by the user as 'raw material', which constitutes an indirect prompt injection surface. The risk is minimized by the skill's structured approach to paraphrasing and 'mining' the content into discrete beats.
- Ingestion points: User-supplied markdown file containing raw material (referenced in SKILL.md).
- Boundary markers: None explicitly defined to encapsulate the raw material within the prompt context.
- Capability inventory: File system read and write operations are used to ingest material and store the resulting article.
- Sanitization: No explicit sanitization or validation of the input markdown content is mentioned in the instructions.
Audit Metadata