The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources including pull request metadata and server responses.
Ingestion points: Pull request titles, bodies, and status metadata are ingested via gh pr view, and external server responses are retrieved via curl health checks in SKILL.md.
Boundary markers: The instructions do not define explicit delimiters or use 'ignore embedded instructions' warnings when the agent interpolates this external content into deployment reports.
Capability inventory: The skill possesses extensive capabilities including repository modification through gh pr merge and git push, infrastructure management via fly and kubectl, and network access via curl.
Sanitization: There is no requirement for the agent to sanitize or validate external content before it is recorded in the permanent deployment record 07-deploy-report.md.

ship-workflow-land