test-service
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to execute shell commands using
bundle exec rspecto run tests within thespec/services/directory. This is a standard and expected operation for a testing-focused skill designed to verify code functionality. - [INDIRECT_PROMPT_INJECTION]: The skill processes project source code (service objects and collaborators) to generate test specifications, which creates a potential surface for indirect prompt injection from within the code being analyzed.
- Ingestion points: Service object source files and collaborator definitions in the local repository.
- Boundary markers: No specific delimiters or warnings to ignore instructions within analyzed files are provided.
- Capability inventory: Execution of Ruby code through the
bundle exec rspecshell command. - Sanitization: No explicit sanitization or validation of the input source code is defined before processing by the agent.
Audit Metadata