probe
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided answers and reasoning to generate a knowledge map file. While this is an ingestion point for untrusted data, the impact is limited to the content of the generated markdown files.
- Ingestion points: User quiz responses (answers and reasons) in SKILL.md.
- Boundary markers: None explicitly defined for the map file generation.
- Capability inventory: The agent is instructed to write and update markdown files in the
.alvar/maps/directory. - Sanitization: The instructions do not explicitly detail sanitization of user input before writing to the map file.
- [COMMAND_EXECUTION]: The skill requires the agent to perform file system operations (creating and updating files) specifically within the
.alvar/maps/directory to track learning progress. This behavior is consistent with the skill's primary purpose of diagnosing and mapping knowledge.
Audit Metadata