apply-stack-conventions
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions require the agent to execute shell commands, specifically
bundle exec rspec, to validate code changes as part of a mandatory TDD cycle described inSKILL.md. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-defined requirements to generate code and associated shell commands for testing, which represents a potential attack surface where malicious input could influence command execution.
- Ingestion points: User-provided feature requirements and implementation details are processed to generate specs and implementation code as described in
SKILL.md. - Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded within user-provided data.
- Capability inventory: Shell command execution through terminal tools is a core requirement of the 'HARD-GATE: TDD Cycle' section.
- Sanitization: No explicit sanitization, validation, or escaping of the generated file paths or command arguments is specified before execution.
Audit Metadata