strategy-red-team
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze untrusted strategy documents, which serves as an ingestion point for external data.
- Ingestion points: The plan or roadmap document provided by the user in the arguments.
- Boundary markers: The instructions do not define specific delimiters to isolate user-provided data from the agent's logic.
- Capability inventory: The skill is strictly informational; it has no access to subprocesses, file-system writes, network tools, or other sensitive capabilities.
- Sanitization: Input text is analyzed directly without filtering or sanitization steps.
- [EXTERNAL_DOWNLOADS]: The skill references external educational resources for methodology.
- Evidence: Informational links to 'productcompass.pm' are included in the 'Further Reading' section for context on assumption prioritization.
Audit Metadata