The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources (GitHub issues), creating a surface for potential manipulation.
Ingestion points: Data is pulled via gh issue list as described in SKILL.md.
Boundary markers: The skill does not define specific delimiters for separating issue content from instructions.
Capability inventory: Capabilities include git logging/versioning and gh issue/release management.
Sanitization: No explicit sanitization or filtering of external issue content is performed.
[COMMAND_EXECUTION]: The skill utilizes standard git and gh CLI commands to interact with the repository's history and issue tracker. These are standard development tools used for their intended purpose.

patch-release