custom-plugin-flutter-skill-backend

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection through its ingestion of external data. \n
  • Ingestion points: SKILL.md demonstrates fetching data from external REST APIs (via dio and http), GraphQL endpoints, and Firebase Firestore collections. \n
  • Boundary markers: The provided code examples do not include delimiters or explicit instructions for the agent to ignore potentially malicious instructions within the fetched data. \n
  • Capability inventory: The skill enables network operations (dio, http, graphql) and secure local storage operations. \n
  • Sanitization: There is no evidence of data sanitization or structural validation for the responses received from external services before they are processed by the application logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 08:50 AM