installing-posthog-in-a-codebase
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references official documentation and library setup guides from the vendor's primary domain.
- [COMMAND_EXECUTION]: The instructions direct the agent to use system package managers (e.g., npm, pnpm, uv, bundle) to install dependencies and suggest using database tools to verify event ingestion.
- [CREDENTIALS_UNSAFE]: The skill promotes secure handling of sensitive data by requiring the use of environment variables for project tokens and ingestion hosts, explicitly advising against hard-coding secrets.
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external manifest files to detect the application framework.
- Ingestion points: Project manifest files such as package.json, pyproject.toml, requirements.txt, Gemfile, composer.json, and go.mod (found in SKILL.md).
- Boundary markers: None identified in the instructions.
- Capability inventory: Dependency installation via shell commands, environment variable modification, and execution of SQL or data schema queries.
- Sanitization: The skill does not specify sanitization or validation steps for the content of the manifest files prior to framework detection.
Audit Metadata