writing-beats
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied markdown files that serve as the raw material for an article. This content is interpolated into the agent's context to generate output.
- Ingestion points: User-provided markdown files of "raw material" mentioned in SKILL.md.
- Boundary markers: The instructions do not define delimiters or specific "ignore" instructions for the ingested material.
- Capability inventory: File system read and write operations are performed to manage the article generation process (SKILL.md).
- Sanitization: No content filtering or validation is specified for the input data.
- [COMMAND_EXECUTION]: The skill instructions direct the agent to perform file system operations, including reading and writing segments of the article to the local disk.
Audit Metadata