The Agent Skills Directory

[SAFE]: No malicious code, hardcoded credentials, or unauthorized network operations were detected. The skill functions as a local documentation linter and validator.\n- [PROMPT_INJECTION]: The skill is subject to an indirect prompt injection surface because it processes untrusted markdown content.\n
Ingestion points: Scans all markdown files in the docs/ directory using the Glob and Read tools (SKILL.md).\n
Boundary markers: Absent; file content is parsed for links and frontmatter without using delimiters to isolate data from instructions.\n
Capability inventory: The skill uses the Edit tool to modify frontmatter and AskUserQuestion for user interaction (SKILL.md).\n
Sanitization: No filtering or sanitization is performed on the ingested markdown content before it is processed by the agent.

check-refs