firebase-firestore

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it is designed to ingest and process data from an external Firebase Firestore database which may contain untrusted instructions.\n
  • Ingestion points: Firestore data access methods such as getDoc, getDocs, and onSnapshot are utilized in SKILL.md and templates/firebase-client.ts.\n
  • Boundary markers: No specific delimiters or instructions are provided to the agent to treat external database content as data rather than instructions.\n
  • Capability inventory: The agent can write template files and execute package installation commands (npm install).\n
  • Sanitization: The provided code samples do not include sanitization or validation logic for data retrieved from the database.\n- [SAFE]: The author name listed in the .claude-plugin/plugin.json file ("Jeremy Dawes") differs from the provided skill author context ("evolv3ai"). Additionally, the skill references and uses official and well-known libraries firebase and firebase-admin from a recognized service provider.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 03:49 AM