instrument-feature-flags
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The instructions recommend running 'npx @posthog/wizard' for automated setup, which downloads and executes the official PostHog initialization tool from the npm registry.
- [COMMAND_EXECUTION]: The skill guides the agent to perform standard package installation and dependency management commands (e.g., 'npm install', 'pip install', 'go get') tailored to the detected project platform.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests local data by analyzing project dependency files (e.g., 'package.json', 'requirements.txt') and lockfiles to identify the technical stack. This involves processing potentially untrusted local data, though the risk is inherent to development tools.
- Ingestion points: Project dependency files and lockfiles in the local directory (STEP 1).
- Boundary markers: Absent.
- Capability inventory: File system write access (STEP 5) and shell command execution (STEP 1-3).
- Sanitization: Absent.
- [DATA_EXFILTRATION]: Reads and manages PostHog project tokens by interacting with environment variable files (e.g., '.env'). It uses the PostHog MCP server's 'projects-get' tool to fetch credentials, adhering to standard secret management practices.
Audit Metadata