nextreme

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill serves as an orchestrator that ingests complex user-provided software tasks and sequences them through various specialized skills (design, build, test, review). This ingestion of untrusted data creates a surface where malicious instructions embedded in a task description could influence downstream operations.
  • Ingestion points: Processes user-provided tasks and feature requests as described in the workflow section (SKILL.md).
  • Boundary markers: The skill does not define specific delimiters or instructions to treat user-provided tasks as data rather than instructions when passing context between phases.
  • Capability inventory: While the skill itself is an orchestrator, it delegates tasks to other components capable of code execution (builds), system design, and repository modification (git).
  • Sanitization: There is no evidence of content sanitization or validation to filter potentially malicious instructions from the initial task request before delegation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 12:59 PM
Security Audit — agent-trust-hub — nextreme