writing-beats
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied markdown files, which represents an ingestion surface for potentially untrusted data.
- Ingestion points: Raw material markdown files provided by the user (SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the processed content.
- Capability inventory: The skill performs file system read and write operations to manage the article generation (SKILL.md).
- Sanitization: No sanitization or filtering of the input text is described.
- [SAFE]: No malicious behaviors, obfuscation, or unauthorized data access patterns were identified. The workflow is limited to processing user-provided documents into structured text.
Audit Metadata