The Agent Skills Directory

[SAFE]: No malicious instructions, dangerous commands, or data exfiltration patterns were detected in the skill instructions. The focus remains on legitimate project documentation tasks.
[DATA_EXPOSURE]: The skill retrieves information from project source code (e.g., server/api/posts/index.post.ts) and documentation directories to generate content. It also mentions a sibling directory '../momei-docs' for worktree-based updates. This level of file access is standard for documentation automation and does not target sensitive system or credential files.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes content from various project files.
Ingestion points: Reads from docs/**/*.md and source code files.
Boundary markers: None are defined in the instructions to isolate ingested content.
Capability inventory: Limited to local file read/write operations for documentation purposes.
Sanitization: No sanitization or validation logic is specified for the ingested content. This surface is considered safe given the skill's restricted operational scope.
[SAFE]: The author is listed as 'GitHub Copilot', which differs from the provided author context. This is interpreted as a descriptive label for the origin of the text rather than a malicious attempt at impersonation.

documentation-specialist