The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill analyzes Rust source files and manifests to determine API changes, which presents an attack surface for instructions embedded in code comments or documentation.\n
Ingestion points: Rust source code files (e.g., src/lib.rs) and Cargo.toml manifest files processed during analysis.\n
Boundary markers: The instructions do not specify any delimiters or safety markers to distinguish between legitimate code and adversarial prompts in the ingested files.\n
Capability inventory: The skill executes several CLI tools including cargo, cargo-semver-checks, cargo-workspaces, cargo-audit, and cargo-deny which perform file and network operations.\n
Sanitization: There is no evidence of sanitization or validation of the input source code before it is interpreted by the agent.\n- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of third-party Rust development tools from the official crates.io registry.\n
Tools: The instructions include commands to install cargo-semver-checks, cargo-workspaces, cargo-audit, cargo-deny, cargo-release, and release-plz.\n
Safety: The skill promotes secure installation practices by using the --locked flag to verify dependency consistency.

rust-semver