The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized data access were found in the skill or its evaluation set. The skill's workflow is focused on productivity and includes explicit safety checks to limit complexity.
[PROMPT_INJECTION]: The skill includes an attack surface for indirect prompt injection by fetching and processing external data from GitHub issues via the gh command. This is a standard feature for development agents but represents an entry point for untrusted content.
Ingestion points: SKILL.md instructs the agent to fetch issue title, body, and labels using gh issue view.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' prompts for the fetched content.
Capability inventory: The skill possesses file write capabilities (Edit) and command execution capabilities (lint/typecheck discovery and execution in SKILL.md).
Sanitization: No sanitization or validation of the fetched issue content is described in the workflow.

oneshot