The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes glab and git commands to perform release management.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted remote content which may contain malicious instructions. 1. Ingestion points: Remote content is ingested via glab release list, glab release view, and glab release download. 2. Boundary markers: No technical delimiters are defined to isolate untrusted data from instructions. 3. Capability inventory: The skill allows creating, updating, and deleting releases. 4. Sanitization: Remote release notes and messages are displayed without sanitization.

glab-release