game-accessibility

Pass

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill accesses the local project codebase to identify platform-specific accessibility requirements and existing feature implementations. This behavior is consistent with the primary purpose of the skill.
  • [PROMPT_INJECTION]: The skill processes user-provided arguments and local codebase files. While this creates an indirect prompt injection surface, the skill includes explicit constraints prohibiting code modification, which limits the potential impact of adversarial content within the analyzed files.
  • [SAFE]: The skill records execution metadata to a local file path (~/.claude/projects/skill-telemetry.md) for telemetry purposes. This is a common pattern for tracking skill performance and does not involve network communication or system-level persistence.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 23, 2026, 10:58 AM
Security Audit — agent-trust-hub — game-accessibility