The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute GitHub CLI (gh) commands to retrieve metadata such as titles, labels, and bodies from issues and pull requests. This is a standard and expected operation for a triage orchestration tool.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources during its analysis phase. * Ingestion points: The body text of issues and pull requests retrieved via gh issue list and gh pr list in SKILL.md. * Boundary markers: There are no explicit instructions for the agent to use delimiters (like XML tags) or ignore embedded instructions when processing these external bodies. * Capability inventory: The agent has access to Bash (for CLI operations), Write (to save reports), and Read tools as defined in the skill's workflow. * Sanitization: The instructions do not define any specific sanitization, escaping, or validation for the content of issue or PR bodies before the agent processes them.

rtk-triage