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_sentiment and search_viewpoints tools 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
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:09 PM