junior-to-senior
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates by analyzing the existing codebase and searching for public documentation and security advisories. These are standard operations for a development-focused AI agent.
- [PROMPT_INJECTION]: The skill is designed to process user-provided or agent-generated plans (indirect ingestion). It includes mitigation strategies such as 'freezing' the input text by restating the artifact in full and adopting an adversarial 'senior' persona to evaluate the content critically, which reduces the risk of the agent following instructions embedded within the ingested data.
- [DATA_EXFILTRATION]: The skill performs web research to identify deprecations and security vulnerabilities. It targets public sources such as official documentation and RFCs rather than transmitting sensitive repository content to external services. The code research phase (Track 1) is kept internal to the repository context.
Audit Metadata