Skills
skills/agents-inc/skills/api-baas-appwrite/Gen Agent Trust Hub

api-baas-appwrite

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill demonstrates patterns for ingesting untrusted data through request objects (e.g., req.bodyJson in serverless functions) and writing that data to a database. This identifies an indirect prompt injection surface where stored instructions could later influence agent behavior.
  • Ingestion points: req.bodyJson and req.bodyText in examples/functions.md.
  • Boundary markers: Absent from documentation examples.
  • Capability inventory: Data persistence operations via tablesDB.createRow, storage.createFile, and account.create.
  • Sanitization: Not explicitly demonstrated in the provided code snippets.
  • [EXTERNAL_DOWNLOADS]: The skill references official integration tools including the appwrite and node-appwrite SDKs and the appwrite-cli for project management. These are standard resources for the platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 01:32 AM