appwrite-python

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill interacts with external, untrusted data that could contain malicious instructions designed to influence the agent's behavior.
  • Ingestion points: The agent retrieves potentially attacker-controlled data using tables_db.list_rows, tables_db.get_row, and by processing request objects like context.req.body_json in the src/main.py function template.
  • Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are suggested when the agent processes data fetched from these sources.
  • Capability inventory: The skill provides the agent with capabilities to modify or delete resources, such as tables_db.delete_row, users.delete, and storage.delete_file, as well as the ability to trigger remote code execution via functions.create_execution.
  • Sanitization: There are no instructions for sanitizing or validating external content before it is interpolated into the agent's context or used to make decisions.
  • [EXTERNAL_DOWNLOADS]: The skill instructions include the installation of the official appwrite Python package from the standard registry using pip install appwrite.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 05:53 AM