instrument-metrics
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill requires the agent to read and write to sensitive environment configuration files (such as .env or .env.local) to retrieve or store PostHog project tokens. This behavior is the intended primary purpose of the skill for secure secret management and it explicitly instructs the agent to avoid hardcoding credentials in the source code.
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes existing codebase content and dependency files to determine the appropriate instrumentation strategy, which creates a potential surface for indirect injection from the analyzed code. However, the logic is limited to identifying platform and framework signatures.
- Ingestion points: Project configuration files (e.g., package.json, requirements.txt, go.mod) and application source code files during the platform detection step.
- Boundary markers: The instructions do not define specific delimiters for separating codebase content from agent instructions.
- Capability inventory: The skill utilizes file system read/write access, environment variable configuration, and PostHog MCP server tools (e.g., projects-get).
- Sanitization: No explicit sanitization of codebase data is performed before processing.
Audit Metadata