prp-orchestrator-agent
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, hardcoded credentials, or suspicious data exfiltration attempts were detected in the skill instructions or templates.
- [COMMAND_EXECUTION]: The skill includes instructions for the agent to run standard local development commands (e.g., npm run build, npm run test). These are considered safe as they are part of the intended workflow for software development and are executed within the user's project context.
- [PROMPT_INJECTION]: The skill directs the agent to read codebase files to identify implementation patterns. While this constitutes a standard attack surface for indirect prompt injection in coding assistants, the skill does not contain any malicious triggers, bypass instructions, or safety filter overrides.
Audit Metadata