skills/crowdin/skills/graphql/Gen Agent Trust Hub

graphql

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user content, including broken GraphQL queries and error messages from the Crowdin Playground. This creates a surface for indirect prompt injection attacks where malicious instructions could be embedded within the data provided for debugging.
  • Ingestion points: User-supplied GraphQL queries and error logs as described in the Core Workflow of SKILL.md.
  • Boundary markers: None; the skill does not use delimiters (e.g., XML tags or triple backticks with headers) or explicit instructions to ignore embedded commands in user data.
  • Capability inventory: The skill's capabilities are limited to text generation and query writing. It does not have access to dangerous tools, file system writes, or network requests.
  • Sanitization: There is no evidence of sanitization or filtering logic applied to the user-supplied input before processing.
  • [SAFE]: The skill references the official vendor documentation at support.crowdin.com. These references are documented neutrally as they are well-known services associated with the skill's primary purpose.
  • [SAFE]: No evidence of sensitive credential harvesting, remote code execution, or persistence mechanisms was found in the provided skill files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 08:56 AM
Security Audit — agent-trust-hub — graphql