relentless-quality-assurance
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to run applications and use computer/browser tools to perform testing. This involves executing code from the development environment, which is a core functional requirement but involves local command execution.
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external codebases via Git and interacts with web applications, creating an attack surface where untrusted data could influence agent behavior.
- Ingestion points: Recent additions to the codebase via Git and application UI/content during testing (SKILL.md).
- Boundary markers: None explicitly defined to delimit external data from instructions.
- Capability inventory: Git command execution, application execution, and browser/computer use tools (SKILL.md).
- Sanitization: No specific sanitization or validation of the ingested code or application responses is mentioned.
Audit Metadata