writing-guidelines
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external, untrusted content (files or patterns provided by the user) to provide writing feedback. This processing of external data creates an attack surface where instructions embedded within the user's documents could potentially influence the agent's behavior.
- Ingestion points: The agent is instructed to "Review the files or patterns provided by the user" and "Read files, check against rules below" (SKILL.md).
- Boundary markers: The instructions do not specify the use of delimiters or provide "ignore embedded instructions" directives to help the agent distinguish between the text to be reviewed and its own operational instructions.
- Capability inventory: The skill focus is restricted to file reading and text output. It does not explicitly call for dangerous tools such as network requests, file writing, or shell command execution, which limits the potential impact of an injection.
- Sanitization: No sanitization, filtering, or validation steps for the input content are described in the instructions.
Audit Metadata