signoz-generating-queries

Pass

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external signals like logs and traces via the signoz_search_logs and signoz_search_traces tools. Because these signals originate from external systems, they could contain malicious instructions designed to manipulate the agent's summary or subsequent tool calls.\n
  • Ingestion points: SigNoz MCP tools used to fetch log bodies and span attributes (SKILL.md).\n
  • Boundary markers: The instructions do not define delimiters (e.g., XML tags) to isolate untrusted content when the agent processes the retrieved data.\n
  • Capability inventory: The skill has access to a variety of SigNoz querying tools and a UI-based apply_filter action, but lacks arbitrary shell or file-write capabilities.\n
  • Sanitization: No specific sanitization logic is provided to filter out potential injection patterns from the observability data before processing.\n- [COMMAND_EXECUTION]: The instructions direct the agent to run the signoz-mcp-setup CLI tool if query tools are missing. This is a vendor-owned resource used for environment initialization.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 13, 2026, 08:14 PM