check-coherence
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external, potentially untrusted files to identify coherence issues, creating a surface for indirect prompt injection.
- Ingestion points: The skill reads a complete file specified by the user in Step 1.
- Boundary markers: There are no delimiters or explicit instructions for the agent to ignore commands or formatting found within the ingested files.
- Capability inventory: The skill is limited to reading text, proposing edits, and applying meaning-preserving fixes. It lacks network access, shell command execution, or file system modifications beyond the target file.
- Sanitization: The skill does not perform sanitization, filtering, or validation of the content being read.
Audit Metadata