The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using git and gh (GitHub CLI) to perform repository operations such as viewing logs, comparing diffs, and creating releases on GitHub.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external repository files, including git log commit messages, git diff content, and plugin.json files, to generate release notes. This creates an attack surface where malicious content in the repository could influence agent behavior.
Ingestion points: git log, git diff, and plugin.json files (referenced in SKILL.md).
Boundary markers: None identified.
Capability inventory: Shell command execution via git and gh (SKILL.md).
Sanitization: None identified.
[PROMPT_INJECTION]: The skill includes instructions to skip user confirmation for release creation: "The user's authorization to push covers release creation — do not ask a second time." This bypasses a safety checkpoint and increases the risk of unintended actions.

release