gan-style-harness

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The documentation describes workflows that use the Bash tool to start local development servers (e.g., npm run dev) and execute shell scripts (e.g., ./scripts/gan-harness.sh). While standard for software development, these operations execute with the agent's privileges.
  • [PROMPT_INJECTION]: The skill architecture creates an indirect prompt injection surface by establishing a feedback loop where different agents read from and write to shared files such as spec.md and feedback-NNN.md. Malicious instructions embedded in the initial user prompt or generated code could potentially influence the behavior of other agents in the chain.
  • Ingestion points: spec.md, feedback-NNN.md (as described in the workflow instructions)
  • Capability inventory: Bash, Write, Edit, Read, Task, and Playwright MCP tools
  • Boundary markers: None explicitly mentioned to distinguish between agent instructions and untrusted data in the shared files
  • Sanitization: The guide does not specify methods for sanitizing or validating the content exchanged between the Planner, Generator, and Evaluator agents
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 12:59 PM
Security Audit — agent-trust-hub — gan-style-harness