ops-inspector

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, unauthorized external downloads, or command injection vectors were found. The skill uses standard MCP tools for CloudBase resource management and refers only to official Tencent Cloud console domains.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data via queryLogs and listFunctionLogs in SKILL.md. This represents a potential surface for indirect prompt injection if log entries contain instructions intended to influence the agent. Current mitigation is the diagnostic-only scope of the skill's capabilities. No explicit sanitization or boundary delimiters are specified for log data processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 03:14 PM