plan-change
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional, guiding the agent to plan changes without writing code. No malicious patterns, obfuscation, or data exfiltration mechanisms were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external feature requests. Although boundary markers are absent, the risk is mitigated by the explicit instruction to avoid code generation and the absence of dangerous tool capabilities.
Audit Metadata