steam-store-launch-ops

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: No attempts to override safety filters, ignore prior instructions, or extract system prompts were detected. The instructions are strictly limited to the task of Steam launch operations.
  • [DATA_EXFILTRATION]: The skill does not access sensitive local file paths or hardcoded credentials. It references official Steamworks documentation, which is appropriate for its intended use.
  • [REMOTE_CODE_EXECUTION]: The skill does not perform any external package installations or execute remote scripts.
  • [COMMAND_EXECUTION]: While the skill uses shell-based tools for reading and editing its own reference files, no arbitrary or dangerous command execution patterns were found.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted input such as Steam page content and user queries. This surface is mitigated by the skill's enforcement of a rigid 'Steam Launch Packet' output structure and explicit 'route-out' instructions that prevent the agent from performing unauthorized tasks based on external input.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 04:31 AM