instrument-logs

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill guides the installation of standard OpenTelemetry SDK packages from official package registries (NPM, PyPI, Go, etc.) to enable observability.
  • [DATA_EXFILTRATION]: The skill configures applications to transmit log data to PostHog's official ingestion endpoint (https://us.i.posthog.com/i/v1/logs). This is the intended primary function of the skill and utilizes the vendor's own infrastructure.
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection as it instructs the agent to analyze application logs which may contain data from untrusted external sources.
  • Ingestion points: Application logs are read and analyzed using MCP tools like logs-query as described in references/debug-logs-mcp.md.
  • Boundary markers: The instructions do not explicitly mandate delimiters or specific instructions to prevent the agent from being influenced by data found within the logs.
  • Capability inventory: The agent has capabilities to modify the codebase, install packages, and write to the file system based on its analysis.
  • Sanitization: No specific sanitization or filtering of log content is recommended before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 03:34 PM