exam-revision-sheet
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, untrusted data provided by the user (such as lecture notes, slides, or textbook excerpts) to generate a summary revision sheet. This configuration presents a surface for indirect prompt injection where malicious instructions could be embedded in the source material.
- Ingestion points: Student-provided material including notes, slides, and review sheets (SKILL.md).
- Boundary markers: The instructions do not define clear delimiters or use "ignore embedded instructions" warnings to isolate the ingested material from the agent's logic.
- Capability inventory: The skill primarily performs text transformation but mentions the capability to interface with external note-taking tools (e.g., Scratchpad connector) to save the output (SKILL.md).
- Sanitization: No sanitization, filtering, or validation steps are included for the input material before it is processed by the agent.
Audit Metadata