The Agent Skills Directory

[COMMAND_EXECUTION]: Uses the Bash tool to perform file system operations, search for identifiers, and execute local scripts.
Employs cat, grep, and ls to read and validate team metadata and agent registries.
Executes npm run update-readmes to automate the update of project documentation based on changes to the team registry.
Uses git diff as a final validation step to review changes before completion.
[PROMPT_INJECTION]: Vulnerable to indirect prompt injection due to the processing of existing project files that could contain malicious instructions.
Ingestion points: Reads data from teams/*.md, agents/_registry.yml, and guides/*.md (File: SKILL.md).
Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard potential instructions embedded within the data being processed.
Capability inventory: The skill possesses significant capabilities including Read, Write, Edit, and Bash execution, allowing it to modify the repository state based on the data it reads.
Sanitization: No sanitization or validation of the content of the ingested files is performed before it is used to update the registry or other team files.

evolve-team