The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to read and process external repository data, including source code, documentation, requirements, and manifests. This creates a surface where malicious instructions embedded in the project files could influence the agent's actions.
Ingestion points: The skill reads repository instructions, task documents, requirements, Git state, source files, tests, and manifests as specified in SKILL.md.
Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the content read from files.
Capability inventory: The skill is capable of writing new test files, installing dependencies, and executing shell commands for test running and environment setup.
Sanitization: There are no instructions for sanitizing or escaping content extracted from these files before using it in the agent's reasoning or command generation.
[COMMAND_EXECUTION]: The skill requires the execution of shell commands to run tests and set up environments. While the instructions emphasize inspecting commands and obtaining user consent, the process involves interpreting and executing logic derived from the project's codebase.
[EXTERNAL_DOWNLOADS]: The skill suggests the installation of a specific dependency (interview-acrazie) via npx. This follows the recognized vendor pattern for the skill author and includes instructions for explicit user consent before installation.

test-retrofitter-acrazie