writing-beats
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill facilitates a collaborative writing process using local files. All file operations (reading and writing) are directed by the user's input and intended for the creation of an article. No suspicious network operations or unauthorized access to sensitive system files were found.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided 'raw material' in markdown format, which presents a surface for indirect instructions. However, the risk is minimal given the skill's specific focus on paraphrasing and structured assembly.
- Ingestion points: Markdown files of raw material provided by the user as described in SKILL.md.
- Boundary markers: No specific delimiters are defined in the instructions to separate data from instructions within the raw material.
- Capability inventory: The skill performs local file read and write operations on paths defined or agreed upon by the user.
- Sanitization: No specific sanitization or escaping of external content is mentioned; the skill relies on the agent's logic to paraphrase and selectively mine the text.
Audit Metadata