fin-guru-output-contract
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill functions as a formatting contract for financial analysis reports. It specifies a six-part structure (Bottom line, Numbers, Assumptions and gaps, Confidence, Evidence, and Disclaimer) to be followed by the agent.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest data from CLI command outputs and external source URLs to populate report tables. This represents a standard attack surface for indirect prompt injection where malicious instructions could be embedded in the source data. However, the skill provides only structural guidelines and does not include mechanisms to override safety filters or execute arbitrary content from these sources.
- [SAFE]: No instances of command execution, network exfiltration, persistence mechanisms, or obfuscated content were detected within the skill instructions.
Audit Metadata