analyze-document
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill is susceptible to instructions embedded in external documents processed by the agent.
- Ingestion points: Untrusted data enters the context via the
readDocumentandparseExceltools defined inSKILL.md. - Boundary markers: Absent. There are no instructions or delimiters specified to ensure the agent ignores commands found within the document contents.
- Capability inventory: The skill utilizes tools for reading text and parsing structured Excel/CSV data.
- Sanitization: Absent. File content is processed directly without validation, escaping, or filtering of potential injection patterns.
Audit Metadata