arabic-code-review

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and review user-provided source code, which serves as a potential attack surface for indirect prompt injection. A malicious user could include hidden instructions within their code to influence the agent's behavior during the review process.
  • Ingestion points: User-provided code snippets or files processed for Arabic compatibility review.
  • Boundary markers: The skill does not define specific delimiters (like triple backticks with unique identifiers) to isolate user content from its instructions.
  • Capability inventory: The skill does not request or use any tools (allowed-tools is empty), network access, or shell execution capabilities, making the injection risk negligible.
  • Sanitization: No input validation or character escaping is defined for the analyzed text.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 04:09 PM