ln-93-configuration-engineer
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data that could contain malicious instructions designed to hijack the agent's workflow.
- Ingestion points: According to SKILL.md, the agent reads manifests, lockfiles, and source code to trace configuration keys and owners.
- Boundary markers: The instructions lack requirements for using boundary markers or 'ignore' instructions when reading these external files.
- Capability inventory: The agent is authorized to use project-native editors and runtime tools to implement changes and verify behavior, creating a risk if injected instructions are followed.
- Sanitization: No explicit content validation or sanitization is required for the external configuration data before processing.
Audit Metadata