exam-forecast
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data from user-provided exam papers (PDF or text), which creates a surface for indirect prompt injection attacks.
- Ingestion points: Workflow Step 1 and 3 involve reading user-supplied documents or file paths to analyze patterns.
- Boundary markers: There are no explicit delimiters or instructions to ignore instructions embedded within the exam materials.
- Capability inventory: The skill has the capability to read local configuration files and write analysis results to the user's home directory.
- Sanitization: The instructions do not specify any validation or sanitization of document content before it is incorporated into the analysis context.
Audit Metadata