zg-ai-strategy-expert
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill demonstrates safe design by incorporating specific rules for handling external content and user-authorized file operations.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from web research and documents (as defined in 'references/evidence-and-research.md'), which presents an attack surface. However, it explicitly instructs the agent to treat this content strictly as data and ignore any embedded instructions or scripts, which is a standard mitigation for its primary analytical purpose.
- [COMMAND_EXECUTION]: The skill includes capabilities to write decision record files to the system ('references/decision-record.md'). This functionality is safely managed by requiring explicit user confirmation before any write operation occurs.
Audit Metadata