The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from an external issue tracker, specifically from the ## Notes section of the map issue. This data is used to dynamically determine which additional skills the agent should consult during execution.
Ingestion points: Reads the body of the wayfinder:map issue from the repository's issue tracker (e.g., GitHub Issues).
Boundary markers: The skill does not define strict delimiters or 'ignore' instructions for the content of the Notes section.
Capability inventory: The agent can invoke the Skill tool, create/modify issues, and spawn subagents for research.
Sanitization: The skill lacks explicit sanitization for tool names or preferences extracted from the tracker before they are used to influence agent behavior.
[DYNAMIC_EXECUTION]: The skill implements dynamic tool invocation by parsing skill names from the tracker's Notes block at runtime. This allows content from an external source to influence which capabilities are active in the agent session.

wayfinder