writing-fragments
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to re-read the contents of a target markdown file before each write operation to preserve user edits. Reading external data that the agent then processes creates a risk of indirect prompt injection if the file contains malicious instructions.
- Ingestion points: The markdown file specified by the user during the session, as described in
SKILL.md. - Boundary markers: None. There are no instructions for the agent to use delimiters or to disregard instructions found within the data.
- Capability inventory: The skill performs file read and file append operations.
- Sanitization: No sanitization or validation logic is applied to the content read from the disk before the agent evaluates it.
Audit Metadata