writing-shape
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest external markdown files ("raw material") and process them into new articles. It lacks explicit instructions for the agent to ignore potential commands or instructions embedded within that raw material, creating a surface for indirect prompt injection.
- Ingestion points: Raw material markdown files passed by the user (referenced in SKILL.md).
- Boundary markers: The skill does not define specific delimiters or instructions to treat the ingested material strictly as data, increasing the risk that embedded text could be interpreted as instructions.
- Capability inventory: The skill utilizes file system read access for the source material and write/append access for the generated article files (referenced in SKILL.md).
- Sanitization: No specific sanitization, validation, or escaping of the input content is defined in the shaping process.
Audit Metadata