gpt-orchestration-auto
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents an engineering orchestration loop that ingests potentially untrusted data from research findings, Git repository drift, and external artifacts. It possesses capabilities to manage agents, subprocesses, and network listeners. This represents an indirect prompt injection surface that is inherent to the skill's primary purpose. 1. Ingestion points: research findings, engineering artifacts, and Git repository state. 2. Boundary markers: Absent. 3. Capability inventory: management of agents, processes, and Git operations. 4. Sanitization: instructions to verify behavior and reconcile findings.
Audit Metadata