The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources that could contain untrusted instructions.
Ingestion points: The skill reads output from gh run list, gh release view, and curl https://pypi.org/pypi/mergify-cli/json (SKILL.md).
Boundary markers: None present to delimit or warn the agent about potentially malicious instructions embedded in external command outputs or API responses.
Capability inventory: The skill can execute powerful repository actions including gh workflow run, gh release edit, and gh release delete (SKILL.md).
Sanitization: No explicit instructions are provided to sanitize or validate the content retrieved from GitHub or PyPI before use.
[COMMAND_EXECUTION]: The skill facilitates the execution of local shell commands for repository and release management.
Evidence: Uses gh (GitHub CLI) for workflow triggers and release modifications, and git log for commit inspection.
[EXTERNAL_DOWNLOADS]: The skill queries an external service to verify publication status.
Evidence: Fetches release metadata from PyPI's official API (https://pypi.org/pypi/mergify-cli/json). PyPI is recognized as a well-known service.

releasing