agent-team-builder

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input to generate agent prompts, creating a surface for indirect prompt injection.\n- Ingestion points: Discovery questions in SKILL.md (process name, pain points, etc.).\n- Boundary markers: No explicit delimiters are present to isolate user data in the generated prompt.md files.\n- Capability inventory: The skill utilizes Read, Write, Bash, and Glob tools.\n- Sanitization: No input validation or filtering is performed on discovery data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:02 PM
Security Audit — agent-trust-hub — agent-team-builder