The Agent Skills Directory

[SAFE]: The skill provides a structured procedural workflow for triage, task execution, and reviews using established tools like the GitHub CLI. No evidence of malicious intent, obfuscation, or unauthorized access was found.\n- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes untrusted data from GitHub issues and comments. While inherent to the skill's purpose, the following factors were identified:\n
Ingestion points: Data is ingested via gh issue view commands and issue lists as described in SKILL.md.\n
Boundary markers: The instructions do not define specific delimiters or instructions to the agent to disregard potential commands embedded within issue content.\n
Capability inventory: The skill has access to powerful tools including Agent, Skill, and Bash to perform parallel implementations and code modifications.\n
Sanitization: Content fetched from GitHub is not sanitized before being passed to sub-agents for implementation.

dispatch