testprof
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run RSpec tests using specific environment variables to activate profilers (e.g.,
TPS_PROF,TEST_STACK_PROF,TEST_MEM_PROF). This is a core part of its diagnostic functionality. - [EXTERNAL_DOWNLOADS]: Recommends adding the
test-profgem to the project'sGemfileand provides a configuration to fetch thesimplecovgem from its official GitHub repository to access specific line-coverage features. - [INDIRECT_PROMPT_INJECTION]: The skill processes and analyzes user-controlled codebase files to provide optimization advice, creating a standard attack surface for indirect injection.
- Ingestion points:
Gemfile,spec/spec_helper.rb,spec/rails_helper.rb, and various application service files. - Boundary markers: None explicitly defined to separate user data from agent instructions.
- Capability inventory: The agent utilizes file read operations and shell command execution (via RSpec profiling).
- Sanitization: No specific validation or filtering of the ingested file content is mentioned.
Audit Metadata