use-rustify-docs
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the
rustify-docs-clitool via the standard Rust package registry (crates.io). It specifies a fixed version (0.2.1) and uses the--lockedflag to ensure dependency integrity. - [COMMAND_EXECUTION]: The skill utilizes several CLI commands (
rustify-docs new,build,check,preview) to manage the lifecycle of a static site. These operations are constrained to the local project environment. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project data (e.g., README, PRODUCT, and DESIGN files) to generate site content, which represents a potential indirect injection surface.
- Ingestion points: Reads project-specific files like AGENTS, README, PRODUCT, and DESIGN (SKILL.md).
- Boundary markers: None explicitly defined for untrusted project data; the agent is instructed to interpret content based on user-defined goals.
- Capability inventory: Subprocess execution of the
rustify-docsCLI tool (SKILL.md, references/rustify-docs.md). - Sanitization: The skill advises against including secrets in static asset directories, but does not specify input sanitization for documentation content.
Audit Metadata