feature-flow

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted repository content (code, instructions, and context) which could contain malicious instructions designed to influence the agents' behavior during the planning or implementation phases.
  • Ingestion points: The main agent gathers context from the repository in SKILL.md (Step 1). The Planner reads supplied context and repository instructions in references/planner.md. The Coder reads repository instructions and existing code in references/coder.md.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands within processed files are present.
  • Capability inventory: The Coder agent in references/coder.md can modify the working tree. The User Flow Tester agent in references/user-flow-tester.md can run CLI commands, call APIs, drive a browser, and invoke other skills.
  • Sanitization: The skill does not specify sanitization or validation steps for the content ingested from the repository.
  • [DYNAMIC_EXECUTION]: The core multi-agent workflow involves generating new code and subsequently executing it to verify requirements.
  • The Coder agent implements the plan in the working tree, and the User Flow Tester agent executes that code via the project's entry points (CLI, API, UI) to validate acceptance criteria.
  • [COMMAND_EXECUTION]: The testing agents are instructed to execute external commands as part of the verification process.
  • Evidence: references/user-flow-tester.md contains instructions for the agent to "run the CLI" and "invoke the skill" to exercise the real entry point of the software under test.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 09:15 PM