sentiment-analyzer
Pass
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill uses vendor-specific tools (strale_sentiment_analyze) to perform sentiment analysis on user-provided text. The implementation follows standard patterns for AI agent skills and does not exhibit any high-risk behaviors such as arbitrary command execution, network exfiltration, or persistence attempts.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (reviews, social posts, articles), which creates a potential surface for indirect prompt injection.
- Ingestion points: External text content described in the SKILL.md summary and body.
- Boundary markers: Absent from the prompt instructions.
- Capability inventory: Restricted to sentiment analysis via sandbase_call_tool as defined in SKILL.md and the API map.
- Sanitization: Not explicitly implemented in the skill instructions.
Audit Metadata