tencent-gaas-manager

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: No patterns of instruction override, jailbreak attempts, or system prompt extraction were detected. The persona instructions are well-structured and remain within the intended domain of game operations management.
  • [DATA_EXFILTRATION]: No sensitive file paths, credential patterns, or unauthorized network operations were identified. Mentions of payment systems (WeChat Pay) and social platforms (WeChat/QQ) are purely contextual descriptions of the gaming ecosystem being discussed and do not involve actual data transmission code.
  • [REMOTE_CODE_EXECUTION]: The skill does not contain any scripts, shell commands, or patterns associated with remote code execution or external content fetching.
  • [COMMAND_EXECUTION]: There are no instances of subprocess spawning, shell execution patterns, or dynamic context injection (!command) within the skill files.
  • [OBFUSCATION]: No obfuscated content, encoded strings, or hidden characters were detected across the provided files.
  • [EXTERNAL_DOWNLOADS]: No external dependencies, package installations, or remote resource downloads are present in the skill definition.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 01:57 AM