writing-shape
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from external files provided by the user to generate articles.
- Ingestion Points: The agent is instructed to read an input markdown file ('the pile') in its entirety as defined in SKILL.md.
- Boundary Markers: There are no explicit instructions to use delimiters or to disregard instructions that might be embedded within the input text.
- Capability Inventory: The agent has permissions to read from the file system and write/append to a user-specified article file across all instruction blocks.
- Sanitization: No input validation or sanitization steps are defined for the content extracted from the raw material pile.
Audit Metadata