instrument-logs

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute standard package manager commands (e.g., npm install, pip install, go get, yarn add, npx expo install) to add OpenTelemetry and PostHog libraries to the user's project.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the download of well-known monitoring and logging libraries from official registries (npm, PyPI, Maven, etc.) and configures application telemetry to be sent to PostHog's ingestion endpoints (e.g., us.i.posthog.com).
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes local codebase files, including manifest files (like package.json or requirements.txt) and source code, to determine the project's platform and logging architecture. This creates a surface where malicious codebase content could theoretically influence agent behavior, though the skill's instructions are narrowly focused on instrumentation.
  • Ingestion points: Project configuration files (e.g., package.json, Podfile, go.mod, pom.xml, requirements.txt) and application source code.
  • Boundary markers: Not explicitly defined in the skill instructions.
  • Capability inventory: File system read/write access, command-line execution for package management, network communication via SDKs, and access to PostHog MCP tools.
  • Sanitization: The skill does not explicitly describe sanitization of the analyzed codebase content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 06:43 AM
Security Audit — agent-trust-hub — instrument-logs