The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to perform framework detection and execute the corresponding test suites for the detected project type.
[COMMAND_EXECUTION]: Utilizes dynamic context injection (the ! syntax) in the SKILL.md file to run cat commands on common configuration files like package.json, pyproject.toml, and pubspec.yaml at skill load time, providing the agent with immediate project context.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes content from untrusted external files within the project directory.
Ingestion points: Project configuration files read by the detect-runner.py script and via the dynamic context injection syntax.
Boundary markers: External file contents are interpolated into the prompt without specific delimiters or instructions to treat the data as untrusted.
Capability inventory: The skill allows access to Bash, Read, and Grep tools.
Sanitization: No sanitization or escaping is applied to the data retrieved from the configuration files before it is presented to the agent.

test