writing-beats
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied raw material to generate content, which could allow instructions within that material to influence the agent.
- Ingestion points: Markdown files provided by the user for processing (SKILL.md).
- Boundary markers: Absent; the skill does not use delimiters or instructions to distinguish untrusted user data from its own core logic.
- Capability inventory: The agent is instructed to read from and write to the local file system to manage and iterate on the generated article (SKILL.md).
- Sanitization: Absent; user material is pulled from the source and used directly to populate narrative beats without explicit validation or escaping.
Audit Metadata