The Agent Skills Directory

[SAFE]: No security vulnerabilities or malicious patterns were detected. The skill performs legitimate local file system operations to list documentation files within the project context.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a minimal attack surface by reading the frontmatter of local markdown files. This is a primary function of the skill for project management and carries negligible risk as the data is only used for display purposes.
Ingestion points: Reads .md files from docs/handoffs/ and its subdirectories.
Boundary markers: Not explicitly required for this display-only use case.
Capability inventory: Limited to directory listing (ls) and file reading.
Sanitization: The agent's standard output formatting for markdown tables handles the display of this metadata safely.

handoff-list