The Agent Skills Directory

[SAFE]: The skill does not contain any malicious payloads, obfuscated code, or suspicious network activities. All external links point to reputable documentation standards, tech blogs, and community guidelines.
[INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it is designed to ingest and act upon content from repository documentation files.
Ingestion points: The agent reads and inventories various files including AGENTS.md, CONTRIBUTING.md, and directories such as docs/** to perform its review and build tasks (inventory-agent.md, docs-framework-agent.md).
Boundary markers: Instructions do not specify the use of delimiters or warnings to prevent the agent from executing instructions found within the documentation files it processes.
Capability inventory: The sub-agents are equipped with Read, Glob, Grep, and LS tools. The skill is authorized to "apply-fixes" to documentation and manage symlinks for tool compatibility (e.g., .cursor to .agents).
Sanitization: There are no instructions provided for sanitizing or filtering input content from the documentation files before the agent processes them.

technical-documentation