setup
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill parses project manifest files such as package.json, pyproject.toml, and Cargo.toml to auto-detect project environments and existing configurations.
- Ingestion points: Project manifests (package.json, pyproject.toml, go.mod, Cargo.toml) and lockfiles.
- Boundary markers: No specific delimiters or safety instructions are used when reading manifest content.
- Capability inventory: Extensive Bash execution capabilities for various package managers (npm, pnpm, bun, uv, go, cargo) and system-level installation (brew).
- Sanitization: No explicit sanitization or validation of manifest data is performed before use.
- [EXTERNAL_DOWNLOADS]: Fetches configuration and tools from official registries and well-known GitHub repositories.
- Evidence: Installs gitleaks and golangci-lint from official GitHub sources; downloads packages from standard registries (npm, PyPI).
Audit Metadata