kernel-ops-ship
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its automated processing of untrusted project data combined with sensitive command execution capabilities.
- Ingestion points: The skill reads and identifies scope from external artifacts including
branchmetadata,PRbodies,featuredescriptions, andtaskdocumentation during Phase 1. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between intended workflow instructions and content originating from the processed data.
- Capability inventory: The skill utilizes the
Bashtool to apply database migrations, deploy application code, and perform network-based health checks. - Sanitization: No procedures for sanitizing or validating the content of the external artifacts are documented before the data influences the deployment logic.
Audit Metadata