search

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill follows best practices for structured search and data presentation, focusing on relevance and freshness of enterprise knowledge.
  • [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it processes external enterprise data. 1. Ingestion points: Enterprise knowledge retrieved via the Glean search tool (SKILL.md). 2. Boundary markers: Absent (uses standard Markdown formatting). 3. Capability inventory: Information retrieval and display only; no subprocess, file system, or arbitrary network access. 4. Sanitization: Absent. The risk is evaluated as safe because the skill's capabilities are restricted and do not allow for the execution of malicious instructions embedded in the data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 06:51 PM
Security Audit — agent-trust-hub — search