ops-inspector

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill uses tools such as envQuery, queryFunctions, queryCloudRun, and queryLogs to retrieve resource metadata and execution logs. These operations are within the scope of the skill's primary purpose for CloudBase resource diagnostics and point to legitimate vendor infrastructure at tcb.cloud.tencent.com.
  • [PROMPT_INJECTION]: The skill processes external data (logs) that could theoretically contain indirect prompt injection content. However, the skill explicitly defines its scope as read-only and diagnostic, stating it should not be used for deploying resources or writing application code, which significantly limits the impact of such vectors.
  • Ingestion points: External logs are ingested via queryFunctions(action="listFunctionLogs") and queryLogs(action="searchLogs") in SKILL.md.
  • Boundary markers: None specific to data interpolation, though the skill provides structured reporting templates.
  • Capability inventory: The skill has read access to logs and resource status across Cloud Functions, CloudRun, and multiple database types (PostgreSQL, MySQL, NoSQL).
  • Sanitization: No explicit sanitization of log content is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 04:16 PM
Security Audit — agent-trust-hub — ops-inspector