sentiment-reality-gap
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [SAFE] (SAFE): No malicious instructions, prompt injection, or obfuscation patterns were detected across the provided documents. The skill follows established analytical frameworks for contrarian investing.
- [NO_CODE] (SAFE): The skill package contains only Markdown documentation and reference templates. There are no Python scripts, Node.js packages, or shell commands that could be executed in the agent's environment.
- [DATA_EXFILTRATION] (SAFE): The skill does not contain any commands or URLs for data exfiltration. It mentions using a separate toolkit (findata-toolkit-cn) for market data, but does not implement any data transport logic itself.
- [Indirect Prompt Injection] (LOW): While the skill analyzes external untrusted data such as social media sentiment and news, it lacks any 'write' or 'execute' capabilities, limiting the risk to potential reasoning bias in the output report.
Audit Metadata