writing-beats
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions define a legitimate workflow for text processing and creative writing. It interacts with the user to select content segments and manages the assembly process using standard file read and write operations without any suspicious or hidden behaviors.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted 'raw material' provided by the user, which presents a surface for indirect prompt injection.
- Ingestion points: The skill reads from a user-supplied markdown file containing raw material and re-reads the generated article file from disk (SKILL.md).
- Boundary markers: No specific delimiters or 'ignore' instructions are used when processing the material.
- Capability inventory: The skill is restricted to file system read/write operations for text content. It lacks capabilities for network access, subprocess execution, or dynamic code evaluation.
- Sanitization: There is no explicit sanitization of the input content, but the lack of dangerous tools or execution environments minimizes the risk of exploitation.
Audit Metadata