support-customer-research
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: The skill file consists entirely of Markdown instructions and does not contain any executable scripts, binary files, or package dependencies.
- [SAFE]: No malicious patterns such as direct prompt injection, obfuscation, or data exfiltration commands were detected. The skill instructions focus on factual synthesis and confidence scoring.
- [PROMPT_INJECTION]: The skill is designed to research external and untrusted content (web searches, forums, and support tickets), which represents a surface for indirect prompt injection. Ingestion points: External web sources and customer support tickets (SKILL.md). Boundary markers: The skill does not define specific delimiters for separating untrusted data from instructions. Capability inventory: The skill does not request or utilize executable capabilities such as shell access or dynamic code evaluation. Sanitization: There are no instructions for sanitizing or filtering the content of the research sources. Given the instructional nature and lack of dangerous tools, this surface does not escalate the verdict.
Audit Metadata