integrate-game-engine
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from project configuration files (e.g.,
package.json,project.godot,*.uproject) to identify game engines and configure automated build or test pipelines. - Ingestion points: Project root files used for engine detection and fingerprinting (referenced in
SKILL.md). - Boundary markers: Not explicitly defined for parsing external project data.
- Capability inventory: Includes powerful tools such as
execute_command,run_build, andrun_tests. - Sanitization: The skill's internal 'Security Guardrails' (specifically ASI05) recommend validating paths and flags against allowlist patterns and avoiding interpolation of untrusted strings into shell commands, which provides partial mitigation.
Audit Metadata