pedagogy-review
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied lecture decks (.qmd or .tex files) which are considered untrusted data sources.
- Ingestion points: The file path provided in the skill arguments is read and its content is passed to a specialized reviewer agent for analysis.
- Boundary markers: The instructions lack specific delimiters or "ignore embedded instructions" warnings for the agent when processing the document content.
- Capability inventory: The skill utilizes Read, Grep, Agent, and Task tools to analyze files and the Write tool to generate reports.
- Sanitization: There is no explicit sanitization or filtering of the file content before it is processed by the analysis agent.
Audit Metadata