rust-documentation
Pass
Audited by Gen Agent Trust Hub on Sep 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute standard Rust build and validation commands, including
cargo test,cargo doc,mdbook,lychee, andtypos. These tools are used for their intended purpose of building and verifying documentation within a local environment.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external project data, such as source code comments and README files, to generate or verify documentation, which is a known attack surface for indirect prompt injection.\n - Ingestion points: Project source code, README.md, and mdBook source files as specified in
SKILL.mdandreferences/mdbook-and-guides.md.\n - Boundary markers: The skill does not define specific delimiters or instructions for the agent to ignore commands embedded in the ingested documentation files.\n
- Capability inventory: The skill possesses capabilities to execute shell commands (
cargo,mdbook,lychee,typos) and read/write project files.\n - Sanitization: The skill recommends a manual quality gate in
references/documentation-release-quality.mdto ensure no credentials or private endpoints are included in the generated output, but lacks automated sanitization of input data.
Audit Metadata