apply-stack-conventions
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill defines a mandatory "HARD-GATE" TDD cycle requiring the agent to execute shell commands, specifically
bundle exec rspec. This is a standard procedure in Ruby on Rails development for validating code correctness and is the primary intended functionality of the skill. - [INDIRECT_PROMPT_INJECTION]: The skill processes and executes test specification files which could theoretically contain malicious instructions if provided by an untrusted source. The workflow involves executing these files via a test runner, which represents an attack surface typical of development tools that interact with user-controlled source code.
- [DATA_EXPOSURE_EXFILTRATION]: No sensitive data access or network-based exfiltration patterns were detected. The skill focuses on local project structure and development conventions.
Audit Metadata