gamedev-router
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to interpret untrusted data from the user's environment to decide which instructions to prioritize.
- Ingestion points: The routing algorithm extracts information from project files (e.g., project.godot, Cargo.toml, package.json) and user request text to identify engines and disciplines.
- Boundary markers: There are no instructions or delimiters provided to the agent to isolate external signals from the routing logic or to ignore potential instructions embedded in filenames or project metadata.
- Capability inventory: The router manages the loading of other specialized skills (e.g., godot-gdscript, unity-physics) which may have significant capabilities including file system modification and code execution.
- Sanitization: The skill does not include logic for sanitizing or validating the project signals it detects, allowing potentially crafted file names or structures to manipulate the routing process.
Audit Metadata