The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, creating a surface for indirect prompt injection. * Ingestion points: Fetches ticket content and linked specifications via a tracker adapter in Step 1 and reads project-specific configuration files (CLAUDE.md) or existing proposals in Step 3. * Boundary markers: The instructions lack explicit delimiters or instructions to ignore embedded commands within the fetched content. * Capability inventory: The skill uses a tracker adapter to fetch tickets, create new documents (issues, comments, or project documents), and modify ticket states (e.g., moving to 'awaiting-decision'). * Sanitization: No sanitization, escaping, or validation of the retrieved external content is specified before it is processed by the agent.

propose