skills/edwinhu/workflows/dev-debug/Gen Agent Trust Hub

dev-debug

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes bash commands to locate reference files and related workflows within the author's plugin cache (~/.claude/plugins/cache/edwinhu-plugins/).
  • [COMMAND_EXECUTION]: The main orchestrator executes regression test commands generated by subagents to verify the success of a bug fix, representing a core functional capability.
  • [PROMPT_INJECTION]: An indirect prompt injection surface is present where user-provided symptoms and codebase content (read by subagents) can influence subagent output and subsequent agent actions.
  • Ingestion points: User-provided symptoms and project files are processed within the agent context in SKILL.md.
  • Boundary markers: The prompt structure uses section headers and delimiters but lacks explicit instructions to ignore embedded instructions within processed data.
  • Capability inventory: Subagents possess file system access (Read, Write, Edit, Grep) and the ability to propose bash commands for execution by the main agent.
  • Sanitization: No sanitization or validation of external data or subagent-generated commands is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 02:36 AM