The Agent Skills Directory

[SAFE]: The skill uses the official GitHub CLI (gh) for its primary operations, such as listing and creating issues, which is standard for developer-oriented tools.
[INDIRECT_PROMPT_INJECTION]: The skill's core functionality involves processing untrusted user input to generate external records, creating a surface for indirect injection.
Ingestion points: The skill explicitly prompts the user to describe problems in their own words, which are then used to populate GitHub issue templates.
Boundary markers: Absent. The instructions do not provide specific delimiters or ignore-instructions to distinguish user-provided bug data from the agent's core instructions.
Capability inventory: The skill utilizes gh issue list and gh issue create, and it is authorized to explore the local codebase to identify relevant domain terminology.
Sanitization: Absent. There is no mention of escaping or validating user-provided strings before they are used in gh issue list search queries or the gh issue create body.

bug-capture