test-service
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied Ruby source code to create corresponding test files, which constitutes a surface for indirect instructions to potentially influence the agent's behavior.
- Ingestion points: Service object source code provided by the user during the spec generation process.
- Boundary markers: Absent; the skill instructions do not define specific delimiters or warnings to isolate user-provided data from agent instructions.
- Capability inventory: File system write access (creating files in spec/services/) and shell command execution (bundle exec rspec).
- Sanitization: Absent; no validation, escaping, or filtering of the input code is described.
- [DYNAMIC_EXECUTION]: The skill generates Ruby script files (RSpec) based on user-provided logic and predefined code templates, then triggers their execution.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute 'bundle exec rspec' in the local environment to verify implementation against the generated specs. This behavior is aligned with the skill's primary purpose of test automation.
Audit Metadata