performance-testing-review-multi-agent-review

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through the analysis of external code.
  • Ingestion points: The skill accepts code snippets, file paths, and Git repositories via the $ARGUMENTS parameter (SKILL.md).
  • Boundary markers: No specific delimiters or instructions are provided to the agent to distinguish between its own operational instructions and the code being analyzed.
  • Capability inventory: The skill contains logic for agent routing, review execution, and insight synthesis, which are applied directly to the untrusted input (SKILL.md).
  • Sanitization: The instructions do not include any steps for sanitizing, validating, or escaping the content of the target project before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 08:59 AM