appwrite-python

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONCREDENTIALS_UNSAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install the appwrite package via pip. This is the official SDK maintained by the vendor.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides templates for Appwrite Functions that ingest untrusted data from request bodies. * Ingestion points: The main(context) function template in SKILL.md processes data from context.req.body_json. * Boundary markers: The examples do not include specific delimiters or warnings to ignore instructions embedded in the user-provided data. * Capability inventory: The skill enables full CRUD operations on databases, storage buckets, and user accounts through the SDK services. * Sanitization: The skill includes a 'Permissions & Roles' section that explicitly warns against overly permissive configurations like Role.any() for write operations.
  • [CREDENTIALS_UNSAFE]: The code examples correctly utilize environment variables (os.environ) for project IDs and API keys, following security best practices for secret management.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 04:08 PM
Security Audit — agent-trust-hub — appwrite-python