english-feedback
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reviews user-provided conversational content to provide language feedback, creating a vulnerability surface where a user could potentially embed instructions to influence the agent.
- Ingestion points: Processes the user's messages from the current session as specified in
SKILL.md. - Boundary markers: No specific delimiters or warnings to ignore embedded instructions are provided.
- Capability inventory: None. The skill does not perform subprocess calls, network operations, or file system writes.
- Sanitization: No explicit sanitization or filtering of external content is defined.
Audit Metadata