glb-mobile-performance-budget

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill defines planning constraints for 3D assets targeted at mobile devices. It does not perform network operations, access sensitive files, or execute arbitrary code. Analysis of the skill instructions and references shows it is a static planning tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-defined inputs like device tiers and scene scopes to determine budget constraints. 1. Ingestion points: User-provided device tier, scene scope, and target context in SKILL.md. 2. Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore instructions embedded in the user input. 3. Capability inventory: The skill is restricted to text generation; it does not invoke file-system writes, network operations, or subprocesses. 4. Sanitization: No sanitization or filtering is performed on user inputs. Risk assessment: The severity is safe as the skill's capabilities are restricted to text generation and have no downstream exploitable actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 07:02 PM