convention-learner
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the project's codebase and configuration files to determine and enforce coding conventions.
- Ingestion points: Project source files (analyzed via get_public_api), .editorconfig, Directory.Build.props, global.json, and CLAUDE.md.
- Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are defined for the data ingestion process.
- Capability inventory: File system analysis via get_project_graph and get_public_api, anti-pattern tracking via detect_antipatterns, and code generation/enforcement capabilities.
- Sanitization: No mention of sanitizing, filtering, or validating content read from the codebase before processing.
Audit Metadata