performance-testing-review-multi-agent-review

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external code artifacts (repositories, snippets, or files) provided through the $ARGUMENTS parameter. This creates a vulnerability surface for indirect prompt injection, where malicious instructions embedded within the code being reviewed could attempt to override the agent's instructions or behavior.
  • Ingestion points: The $ARGUMENTS variable in SKILL.md acts as the primary entry point for untrusted external data.
  • Boundary markers: The instructions lack explicit delimiters or "ignore embedded instructions" warnings to separate the user-provided code from the agent's operational logic.
  • Capability inventory: The skill coordinates a network of specialized agents (Security, Architecture, Performance) to perform deep analysis and synthesis of the provided input, which increases the impact if the agent is successfully manipulated by injected content.
  • Sanitization: No evidence of input validation or sanitization is present in the orchestration logic or instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 02:39 AM
Security Audit — agent-trust-hub — performance-testing-review-multi-agent-review