screening
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data from CSV files and user-provided inputs for screening purposes. This functionality creates an attack surface where malicious instructions could be embedded within the data to influence the agent's decision-making.
- Ingestion points: 'uploaded CSV' mentioned in SKILL.md for batch screening.
- Boundary markers: None identified in the provided skill instructions.
- Capability inventory: File reading of CSV data and generation of Excel reports.
- Sanitization: No specific input validation or data sanitization procedures are described in the workflow.
Audit Metadata