writing-shape
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFEMETADATA_POISONINGINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs file read and write (append) operations on paths provided by the user. These operations are restricted to the intended purpose of processing raw material and creating a document. No unauthorized access to sensitive system paths or credentials was found.
- [METADATA_POISONING]: The word 'exploit' in the skill description refers to the 'explore vs exploit' strategy in content creation and does not indicate malicious intent or deceptive practices.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided text which is an ingestion point for external content. Ingestion point: input file reading in SKILL.md. Boundary markers: None. Capability inventory: File read and append. Sanitization: None, though the skill encourages paraphrasing.
Audit Metadata