doc-review
Pass
Audited by Gen Agent Trust Hub on Aug 17, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it is designed to ingest and process arbitrary user-provided documents without sufficient boundary protections.
- Ingestion points: The skill reads the entire content of user-uploaded or referenced documents as specified in the
Executionsection ofSKILL.md. - Boundary markers: There are no instructions or delimiters (like XML tags or specific 'ignore' directives) provided to help the agent distinguish between its instructions and potentially malicious commands embedded within the document being reviewed.
- Capability inventory: The skill does not explicitly request or use high-risk tools (e.g., shell access, network requests, or file system modifications), which limits the impact of potential injection attacks.
- Sanitization: The skill lacks logic to sanitize or filter the content of the document before the agent processes it for feedback.
Audit Metadata