The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process a wide variety of project files, including source code (src/), manifests (Cargo.toml), and test artifacts (fixtures/, snapshots/, fuzz/). This creates an attack surface for indirect prompt injection where malicious instructions embedded in these files could influence the agent's behavior. The skill lacks explicit sanitization or boundary marker requirements for this data.
[COMMAND_EXECUTION]: The skill frequently recommends the execution of shell commands using the cargo toolchain (e.g., cargo test, cargo bench, cargo fuzz) as well as other task runners like just and make. These capabilities are central to the skill's purpose but represent a potential execution vector for malicious instructions received through indirect prompt injection.

rust-test