The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted data from various sources and transform it into GitHub issues without a manual review step.
Ingestion points: Processes user-provided "braindump, doc, spec, or conversation" as stated in SKILL.md.
Boundary markers: The instructions do not specify any delimiters or warnings to ignore instructions embedded within the source data.
Capability inventory: The skill utilizes gh issue create and gh api to write content directly to a repository.
Sanitization: No validation or sanitization is performed on the incoming data before it is formatted into an issue body.
[COMMAND_EXECUTION]: The skill instructions in SKILL.md direct the agent to execute shell commands using the GitHub CLI (gh) for creating issues and managing milestones.
[DATA_EXPOSURE]: The skill accesses repository information via gh repo view to determine the target for automated actions.

capture-issues