The Agent Skills Directory

[SAFE]: The skill provides documentation and guides for standard software release workflows. It does not contain any malicious patterns such as obfuscation, exfiltration, or unauthorized command execution.- [COMMAND_EXECUTION]: The skill defines clear boundaries for command execution using the allowed-tools frontmatter, restricting the Bash tool to only git and npm version commands. This follows the principle of least privilege.- [INDIRECT_PROMPT_INJECTION]: The skill processes project metadata from files like package.json and CHANGELOG.md. While this presents a potential ingestion surface for indirect prompt injection, the skill is configured with disable-model-invocation: true, which mitigates risks associated with the model interpreting data as new instructions.- [EXTERNAL_DOWNLOADS]: The documentation references standard development utilities and packages like conventional-changelog-cli and @semantic-release plugins. These are well-known tools within the development ecosystem and are cited for legitimate workflow automation.

release