discover-brand

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill orchestrates discovery and retrieval of content from various external enterprise platforms (Notion, Slack, Confluence, etc.) to generate brand guidelines. This introduces an indirect prompt injection surface.
  • Ingestion points: Data retrieved from connected platforms including Google Drive, Slack, and Notion (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used when processing retrieved content (SKILL.md).
  • Capability inventory: The skill writes to the local file system and delegates sub-tasks to other agents (SKILL.md).
  • Sanitization: There is no mention of escaping or validating content retrieved from external platforms (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 03:21 PM
Security Audit — agent-trust-hub — discover-brand