escalation-manager
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data, creating a surface for indirect prompt injection.\n
- Ingestion points: The skill collects and analyzes data from customer tickets, chat logs, and social media mentions as part of its VOC analysis and reporting workflows.\n
- Boundary markers: The instructions do not define explicit boundary markers or delimiters to isolate untrusted data, nor do they include warnings for the agent to ignore instructions embedded within the feedback content.\n
- Capability inventory: The skill's primary function is text analysis and Markdown report generation. No dangerous capabilities such as shell access, network exfiltration, or arbitrary file modification were detected in the provided skill files.\n
- Sanitization: The skill contains an explicit instruction to mask customer personal information in reports, providing a measure of protection against accidental data exposure.
Audit Metadata