cfo
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns such as prompt injection, data exfiltration, or remote code execution were found in the skill.
- [PROMPT_INJECTION]: While the skill contains no direct injection, it has a surface for indirect prompt injection. 1. Ingestion points: Reads financial documents from
docs/finance/and market data viaWebSearch. 2. Boundary markers: No delimiters or ignore instructions are used. 3. Capability inventory: Permission to write todocs/finance/and editHUMAN_AGENDA.md. 4. Sanitization: No sanitization of external data is specified. - [EXTERNAL_DOWNLOADS]: No external software dependencies or remote scripts are downloaded or executed.
- [COMMAND_EXECUTION]: No shell commands or subprocess calls are present in the skill definition.
Audit Metadata