defold-skill-maintain

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The script scripts/fetch_proto.py downloads official release information from d.defold.com and the Defold SDK zip archive from the official defold/defold GitHub repository. These downloads target official and well-known sources for the Defold game engine.
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute the included scripts/fetch_proto.py script to update local Protobuf schema assets.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves fetching Markdown content from official Defold documentation URLs and incorporating that data into other skill files, creating a potential surface for indirect prompt injection from the remote content. 1. Ingestion points: Capability 1 in SKILL.md fetches data from https://defold.com/llms/apis.md, https://defold.com/llms/manuals.md, and https://defold.com/llms/examples.md. 2. Boundary markers: The instructions do not specify the use of delimiters or warnings for the fetched content. 3. Capability inventory: The agent is authorized to modify skill files and execute the scripts/fetch_proto.py script. 4. Sanitization: No explicit sanitization or validation of the remote Markdown content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 05:24 PM
Security Audit — agent-trust-hub — defold-skill-maintain