lore-capture
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to capture business rules, product logic, and gotchas from user conversations and store them in the project's documentation (
docs/lore/). - Ingestion points: Data is sourced directly from user conversation input.
- Boundary markers: The skill does not define specific delimiters for the content being written to markdown files.
- Capability inventory: The skill requires file-writing capabilities to create and update markdown files in the local repository.
- Sanitization: No explicit sanitization of the user-provided 'lore' is performed before storage. While this represents a surface for indirect prompt injection if the stored documentation is later read by an AI, it is the primary intended purpose of the skill.
Audit Metadata