enterprise-search-source
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists exclusively of markdown documentation and contains no executable scripts, automation code, or shell commands.
- [SAFE]: No security issues were detected. The contents are limited to guiding the agent on how to prioritize and manage search queries across connected enterprise tools.
- [PROMPT_INJECTION]: The skill documents a surface for Indirect Prompt Injection as it is designed to process data from various external enterprise sources.
- Ingestion points: External data enters the agent context via MCP tools for chat, email, cloud storage, CRM, and project tracking as described in
SKILL.md. - Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts within the retrieved search results.
- Capability inventory: The agent is authorized to search and read contents from multiple external platforms.
- Sanitization: No sanitization or validation of the external search content is mentioned in the instructions.
Audit Metadata