mastery-assessment
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests content from user-provided notes and question banks to generate assessment probes, creating an indirect prompt injection surface.
- Ingestion points: The agent reads from
assessments/question-banks/and evergreen notes tagged with specific modules. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are defined for the ingested content.
- Capability inventory: The skill can generate assessment logs in
assessments/log/and propose updates to note metadata. - Sanitization: There is no logic specified for sanitizing or validating the content of the notes before they are processed by the agent.
Audit Metadata