exploring-apm-traces

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a standard instructional guide for using vendor-specific MCP tools (posthog:*) to query and analyze application performance monitoring data. All resources and tools referenced align with the author's identity (PostHog).
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data (OpenTelemetry spans) retrieved from PostHog.
  • Ingestion points: External span data enters the agent context via posthog:query-apm-spans and posthog:apm-trace-get as described in SKILL.md.
  • Boundary markers: None identified in the skill instructions.
  • Capability inventory: No file system writes, subprocess executions, or arbitrary network operations are defined within the skill content.
  • Sanitization: No explicit sanitization or validation of the ingested span attributes is described.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 05:30 PM