k12-lesson-prep
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external lesson materials to help teachers prepare. This creates a potential surface for indirect prompt injection if the external materials contain malicious instructions designed to influence the agent's behavior.\n
- Ingestion points: The instructions in SKILL.md direct the agent to "Get the actual lesson" as the primary source of data for its tasks.\n
- Boundary markers: The skill does not define specific delimiters or "ignore" instructions to separate the external lesson content from the agent's core logic, which is a standard risk factor for data-driven tasks.\n
- Capability inventory: The skill possesses the capability to write a structured summary to a file named
prep_note.mdwithin the system's output directory.\n - Sanitization: There are no explicit requirements in the instructions for sanitizing or validating the contents of the ingested lesson before the agent processes and summarizes it.
Audit Metadata