The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the gh CLI and Linear MCP tools to perform issue management tasks, such as creating maps, creating child tickets, and resolving issues. These operations are legitimate and expected for the skill's intended purpose.
[PROMPT_INJECTION]: The skill interacts with external, potentially user-controlled data from issue trackers, which presents a surface for indirect prompt injection.
Ingestion points: In SKILL.md (under "Work through the map"), the skill reads map bodies and ticket descriptions from GitHub, Linear, or local markdown files.
Boundary markers: The skill uses specific Markdown headers (e.g., ## Question, ## Destination) as templates to structure data, though it does not provide explicit instructions to ignore instructions embedded within those data fields.
Capability inventory: The skill has the ability to execute shell commands (gh CLI), write to the local filesystem (.scratch/ directory), and invoke other agent skills (research-plus, grill-me-plus, etc.).
Sanitization: The skill does not implement specific sanitization or filtering for the data fetched from the trackers, relying instead on the agent's default processing capabilities.

wayfinder-plus