The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes data from an external issue tracker, creating a surface for indirect prompt injection. \n- Ingestion points: The skill reads ticket bodies (Question), map metadata (Notes, Destination), and issue titles from the tracker as described in SKILL.md. \n- Boundary markers: No specific delimiters or instructions are used to isolate or ignore instructions that may be embedded in the fetched tracker data. \n- Capability inventory: The agent can create, modify, and close issues, and invoke subagents like /research and /prototype which can perform git operations and documentation analysis. \n- Sanitization: The instructions do not mention any sanitization or validation steps for content retrieved from the external issue tracker. \n- [COMMAND_EXECUTION]: The skill references the use of the /setup-witify-skills command to configure the tracking environment. This is a vendor-provided utility tool associated with the skill author.

wayfinder