instrument-metrics
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes local project files such as package.json, requirements.txt, and source code to detect platforms and instrumentation points. This ingestion of codebase data creates a surface for indirect prompt injection if those files contain malicious instructions.\n
- Ingestion points: Dependency files (package.json, requirements.txt, pyproject.toml, go.mod, pom.xml) and application source code.\n
- Boundary markers: None identified.\n
- Capability inventory: File reading, file writing (instrumentation), and environment variable configuration.\n
- Sanitization: None identified.\n- [COMMAND_EXECUTION]: The skill instructs the agent to execute installation commands like
npm install posthog-nodeandpip install posthog. These refer to official, vendor-provided libraries.\n- [EXTERNAL_DOWNLOADS]: The skill references official installation sources, including a Helm chart for the PostHog metrics agent hosted on GitHub Container Registry.
Audit Metadata