agent-coordination
Fail
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: HIGHPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION] (HIGH): The skill demonstrates a significant Indirect Prompt Injection surface (Category 8) by orchestrating high-privilege agents over untrusted data. 1. Ingestion points: Source code and development tasks across multiple languages (SKILL.md). 2. Boundary markers: Not specified in the provided documentation. 3. Capability inventory: 'test-runner' (subprocess/code execution), 'feature-implementer' (file system write), and 'refactorer' (file system write) (SKILL.md). 4. Sanitization: None identified in provided documentation.
- [NO_CODE] (INFO): The submitted file is a Markdown documentation file and does not contain functional scripts, system prompts, or configuration files.
Recommendations
- AI detected serious security threats
Audit Metadata