mock-exams
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes a workflow where the agent processes external data, such as practice exams and scoring keys, to perform diagnostic analysis.
- Ingestion points: The agent ingests user-provided exam questions, answers, and scoring criteria during the "Forensic Error Autopsy" phase (SKILL.md, Step 3).
- Boundary markers: The instructions do not define specific delimiters or instructions to the agent to disregard potential instructions embedded within the processed exam materials.
- Capability inventory: The skill does not request access to high-risk tools (e.g., network access or shell execution), which significantly limits the potential impact of an injection.
- Sanitization: There is no evidence of input validation or sanitization for the data being analyzed during the remediation and autopsy steps.
Audit Metadata