faf-wizard
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends the installation and execution of external tools, specifically the 'faf-cli' package and 'claude-faf-mcp' server from npm, which are used to analyze projects and sync AI context.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves scanning untrusted local project data to generate instructions for AI agents, creating a potential vector for malicious data to influence agent behavior.
- Ingestion points: The tool parses project manifests such as 'package.json', 'Cargo.toml', and 'pyproject.toml', as well as human-readable documentation like 'README.md'.
- Boundary markers: The skill does not explicitly describe the use of delimiters or instructions to ignore embedded commands when processing extracted project text.
- Capability inventory: The skill facilitates file system reads (for project analysis) and file system writes (for syncing context to files like '.cursorrules' or 'CLAUDE.md').
- Sanitization: There is no documented validation or sanitization of the content extracted from external project files before it is interpolated into AI context files.
Audit Metadata