writing-fragments
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read the contents of a markdown file from the local file system to ensure that any manual edits made by the user are preserved. This action creates a point of entry for indirect instructions if the file content is untrusted or compromised.
- Ingestion points: The agent reads the contents of the user-defined markdown file before each write operation.
- Boundary markers: No delimiters or specific instructions are provided to the agent to treat the file content solely as data or to ignore potential instructions within it.
- Capability inventory: The skill utilizes file reading and writing capabilities.
- Sanitization: There is no process for sanitizing or validating the text read from the file.
Audit Metadata