agent-creator

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The scripts/init_agent.mjs script is vulnerable to indirect prompt injection via schema confusion. It interpolates the user-provided --instructions argument into a triple-quoted TOML string without escaping the """ delimiter. This allows an attacker (or a malicious user prompt) to terminate the instruction string and inject arbitrary TOML configuration keys.
  • Ingestion points: CLI arguments passed to scripts/init_agent.mjs (specifically --instructions).
  • Boundary markers: The script uses triple quotes (""") to encapsulate instructions but fails to sanitize the content for existing triple-quote sequences.
  • Capability inventory: The skill writes .toml files to .codex/agents/, which defines the capabilities (including tool access, MCP servers, and permissions) for future agent sessions.
  • Sanitization: The normalizeMultiline function only handles newline character replacement and does not perform any escaping or validation of the TOML structure against injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 01:55 PM
Security Audit — agent-trust-hub — agent-creator