The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and process content from external references provided by the user, which could contain instructions intended to influence the agent's behavior.
Ingestion points: SKILL.md instructs the agent to fetch context from spec paths, issue numbers, or URLs provided by the user.
Boundary markers: The instructions lack specific delimiters or instructions to treat the fetched external content as non-executable data.
Capability inventory: The skill has access to explore the codebase, write local files within the .scratch/ directory, and publish issues to external platforms like GitHub or Linear.
Sanitization: There is no evidence of sanitization, filtering, or validation of the fetched external content described in the skill instructions.
[EXTERNAL_DOWNLOADS]: The skill performs network operations to retrieve information from external URLs and issue tracker platforms during its context-gathering phase.

to-tickets