The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized data exfiltration behaviors were detected.
[PROMPT_INJECTION]: The skill defines a data ingestion point in SKILL.md where user input from $ARGUMENTS is processed within <issues> tags. While this presents an indirect prompt injection surface, the risk is managed through the use of boundary markers and a mandatory multi-stage review process (spec-compliance and code quality) before changes are integrated. Capabilities are limited to development-related tasks like code modification, testing, and git operations.
[COMMAND_EXECUTION]: The skill orchestrates several specialized subagents (e.g., fullstack-developer, git-manager, tester) to perform software maintenance tasks. These operations are within the expected scope of a development tool and are governed by strict file ownership rules described in the instructions.

fix-parallel