writing-shape
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection by processing external, untrusted content provided as the 'raw material pile'.
- Ingestion points: The agent is instructed to read an input markdown file ('pile') in full (SKILL.md).
- Boundary markers: The instructions do not define boundary markers or delimiters to separate instructions from user-provided data.
- Capability inventory: The skill performs file system read and write operations, including appending content to an article file based on the input material.
- Sanitization: There is no evidence of sanitization, escaping, or validation of the content pulled from the raw material file.
Audit Metadata