iso-13485-certification
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-provided documentation (Quality Management System files) to identify compliance gaps.
- Ingestion points: The
scripts/gap_analyzer.pytool recursively scans a user-specified directory and reads the content of text and markdown files. - Boundary markers: There are no explicit boundary markers or instructions to the agent to treat the contents of the user's documents as untrusted data or to disregard embedded instructions.
- Capability inventory: The agent has the ability to read local files, execute a bundled Python script, and write new documentation based on templates.
- Sanitization: No sanitization or validation of the input document content is performed before the agent reviews the results and presents findings to the user.
Audit Metadata