line-editor
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted prose which could contain malicious instructions.
- Ingestion points: Processes text from user prompts, attached files, and manuscript data fetched via the MCP connector (SKILL.md).
- Boundary markers: Does not implement specific delimiters or safety instructions to isolate user-provided prose from the skill's operational instructions.
- Capability inventory: Includes reading entire manuscripts, performing cross-file searches, and writing marginalia notes back to files via MCP.
- Sanitization: No mechanisms for escaping or validating the content of the prose input are described.
Audit Metadata