rails-dev-pipeline

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the bundle exec rspec command to run tests that are dynamically generated by an AI agent during the testing phase in SKILL.md. This involves the execution of code created at runtime by an LLM.\n- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by interpolating untrusted user requirements directly into agent instructions across a multi-step pipeline.\n
  • Ingestion points: User-provided requirements are ingested via args.requirements in Phase 1 (SKILL.md).\n
  • Boundary markers: None. User requirements are directly interpolated into the prompt string without delimiters or instructions to ignore embedded commands.\n
  • Capability inventory: The skill possesses the capability to modify the local file system and execute shell commands (bundle exec rspec) in Phase 2 (SKILL.md).\n
  • Sanitization: No sanitization or validation is performed on the input string before it is passed to the agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 02:20 PM
Security Audit — agent-trust-hub — rails-dev-pipeline