think-backcasting
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions and examples are strictly text-based and provide a framework for strategic planning. There are no scripts, command-line executions, or network-enabled tools included.
- [INDIRECT_PROMPT_INJECTION]: The skill involves processing user-supplied descriptions of future states and milestones. Although this represents an ingestion point for untrusted data, the skill does not possess any exploitable capabilities such as file system modification, network exfiltration, or code execution. The output is restricted to producing a structured markdown artifact.
Audit Metadata