Skills
skills/posthog/ai-plugin/exploring-apm-traces/Gen Agent Trust Hub

exploring-apm-traces

Pass

Audited by Gen Agent Trust Hub on May 6, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes vendor-specific tools such as posthog:query-apm-spans and posthog:apm-trace-get to analyze performance data. These tools are used as intended for service trace investigation.
  • [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface through the ingestion of external OpenTelemetry span data.
  • Ingestion points: External trace data enters the context through posthog:query-apm-spans and posthog:apm-trace-get (SKILL.md).
  • Boundary markers: The instructions do not define specific delimiters or guardrails to treat the external trace data as untrusted.
  • Capability inventory: The agent has access to posthog:execute-sql as mentioned in SKILL.md.
  • Sanitization: The skill does not provide instructions for sanitizing or validating ingested span attributes before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 6, 2026, 04:27 PM