fda-consultant-specialist
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides analysis scripts that ingest content from external project files, which creates a potential surface for indirect prompt injection.
- Ingestion points: The scripts
fda_submission_tracker.py,qsr_compliance_checker.py, andhipaa_risk_assessment.pyread documentation and source code from user-defined project paths. - Boundary markers: The agent instructions in
SKILL.mddo not include specific delimiters or boundary warnings for the agent to use when processing the output of these analysis scripts. - Capability inventory: The provided scripts are limited to local, read-only file operations and regex-based analysis; they lack network access, file-writing capabilities, or arbitrary code execution.
- Sanitization: The scripts do not perform sanitization or filtering of the content read from the project files, which could allow instructions embedded within project documents to influence the agent's behavior.
Audit Metadata