writing-shape
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied markdown files, creating a surface where instructions embedded in the material could potentially influence agent behavior.
- Ingestion points: The agent is instructed to read an input markdown file containing fragments or unstructured prose, referred to as the "input pile" in SKILL.md.
- Boundary markers: Absent; the instructions direct the agent to "Read it end-to-end" and "mine the pile" without establishing delimiters or safety constraints for the content of the file.
- Capability inventory: The skill requires file read access for the source material and file write/append access to build the output article as described in SKILL.md.
- Sanitization: Absent; the skill does not describe any filtering, validation, or escaping of the external content before it is processed or incorporated into the resulting article.
Audit Metadata