The Agent Skills Directory

[SAFE]: The skill defines a structured workflow for tracking project progress through markdown files. No malicious behaviors such as data exfiltration, obfuscation, or unauthorized command execution were detected.
[PROMPT_INJECTION]: The skill has a potential surface for indirect prompt injection because it reads and processes existing tickets which may contain untrusted content. This risk is considered low due to the planning-oriented nature of the skill and requirements for human-in-the-loop confirmation.
Ingestion points: Processes ticket data from docs/tickets/ using the ticket-parse tool as described in SKILL.md.
Boundary markers: No explicit markers are used to isolate parsed ticket content from the agent's internal instructions.
Capability inventory: Includes the ability to write project specs (to-spec), create tickets (to-tickets), and route tasks to execution tools (execute-ticket).
Sanitization: No specific content sanitization or validation of the content within processed tickets is documented.

wayfinder