final-assignment-citation-review
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted external data, such as student reports and notebooks. This creates a potential attack surface where malicious instructions embedded in the analyzed materials could attempt to override the agent's evaluation logic. The skill includes a mitigation in its 'Anti-Patterns' section advising against treating external content as trusted instructions.
Audit Metadata