The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute local shell commands including cargo build, git add, git commit, and a project-specific test runner ./target/release/caro.
[PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection as it processes output from test failures to modify the system prompt stored in src/backends/embedded/embedded_backend.rs. 1. Ingestion points: Test failure logs from ./target/release/caro test in SKILL.md. 2. Boundary markers: No boundary markers or instructions to ignore embedded commands are specified for the prompt editing process. 3. Capability inventory: The skill has capabilities to write to project source files and execute shell commands. 4. Sanitization: No sanitization or validation of test output is described before it is incorporated into the improved prompt.

prompt-tuner