The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill directs users to a third-party GitHub repository (github.com/joaquinhuigomez/agent-eval) to download and install a CLI tool. This repository is not affiliated with the skill author or recognized trusted organizations.
[COMMAND_EXECUTION]: The instructions and workflow involve executing shell commands via the agent-eval tool and running arbitrary judge commands (e.g., pytest, npm run build) defined in YAML task files.
[INDIRECT_PROMPT_INJECTION]: The skill's architecture for processing task definitions presents a surface for indirect prompt injection as it executes instructions derived from external data files.
Ingestion points: YAML task definition files located in the tasks/ directory, as described in SKILL.md.
Boundary markers: No specific boundary markers or instruction-ignoring delimiters are mentioned for the prompt or command fields.
Capability inventory: The skill uses Bash, Read, Write, and Edit tools, and executes shell commands specified in the configuration's judge criteria.
Sanitization: There is no evidence of sanitization or filtering applied to the commands or prompts before they are executed or passed to the agent.

agent-eval