northstar-architecture-refocus
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security risks were detected in the skill instructions. The scope is limited to diagnostic project analysis.- [INDIRECT_PROMPT_INJECTION]: The skill processes input provided by the user after a specific command. This surface is evaluated as safe due to explicit behavioral constraints. 1. Ingestion points: User-provided text following the command suffix. 2. Boundary markers: Not specified for the input string. 3. Capability inventory: The skill explicitly restricts the agent to a 'plan-only' mode, forbidding production code edits, worker processes, and execution authorization. 4. Sanitization: None observed, but the restrictive operational scope effectively mitigates potential exploitation.
Audit Metadata