lecture-source-pack
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions designed to guide an AI agent in organizing legal research and creating lecture outlines. It contains no executable scripts, automated commands, or remote dependencies.
- [DATA_EXPOSURE]: The instructions explicitly promote safe data handling by directing the user/agent to ensure personal practical cases are authorized and de-identified before use, and specifically warns against sending case files to commercial MCP platforms.
- [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill ingests user-provided lecture topics, audience details, and duration via the
argument-hintfield. - Boundary markers: None explicitly defined for input encapsulation.
- Capability inventory: No capabilities for file writing, network operations, or subprocess execution are present in the skill.
- Sanitization: The skill provides manual instructions for the user to sanitize/de-identify private data, which serves as a conceptual safeguard. Given the lack of dangerous capabilities, the risk of injection leading to harm is negligible.
Audit Metadata