bid-strategy-planner
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill incorporates defensive instructions against indirect prompt injection by explicitly telling the agent to treat external data exports (CSVs, screenshots) as untrusted and to ignore any instructions embedded within them.
- [SAFE]: External resource links are restricted to the author's own GitHub repository (github.com/aaron-he-zhu), which is consistent with the skill's origin and metadata.
- [SAFE]: The skill operates on local state and memory files within expected directory structures and does not perform any unauthorized network operations or credential harvesting.
- [SAFE]: No obfuscation, dynamic code execution, or privilege escalation patterns were found in the skill instructions or reference materials.
Audit Metadata