sentiment-shift
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill processes untrusted external data which could potentially contain hidden instructions.
- Ingestion points: External data enters the agent context through the
get_ticker_sentimentandsearch_viewpointstools defined in the 'Instructions' and 'Tool Sequence' sections. - Boundary markers: The prompt template for 'Present Results' does not use explicit delimiters or instructions to treat the '[representative view]' as untrusted data.
- Capability inventory: The skill is restricted to information retrieval and formatting. It does not possess capabilities for file system modification, network exfiltration, or arbitrary command execution.
- Sanitization: No sanitization or filtering is performed on the content retrieved from external viewpoints before it is presented to the user.
Audit Metadata