The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the platform-specific open command to display a generated HTML dashboard in the user's browser.
[EXTERNAL_DOWNLOADS]: The generated dashboard includes a reference to the Chart.js library hosted on a public CDN, which is a well-known service used for data visualization.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes user-provided test inputs and evaluation criteria to autonomously modify other agent skills. Ingestion points: User-defined target skill path, test inputs, and evaluation criteria in SKILL.md. Boundary markers: No explicit delimiters or isolation instructions are used to separate untrusted user data from the skill's logic. Capability inventory: The agent is authorized to read and write local files, execute other agent skills, and run shell commands. Sanitization: The skill does not perform validation or sanitization of external content before incorporating it into the optimization process.

autoresearch