installing-posthog-in-a-codebase
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external documentation from posthog.com and local project files, which could potentially contain malicious instructions intended to influence agent behavior.
- Ingestion points: Remote documentation files from posthog.com and local manifest files like package.json, pyproject.toml, and requirements.txt.
- Boundary markers: None identified in the skill instructions to separate external untrusted data from the agent's instructions.
- Capability inventory: Shell command execution (package installation), file system writes (editing .env files), and database access (execute-sql).
- Sanitization: No specific mechanisms for sanitizing or validating the content retrieved from external documentation are described.
- [COMMAND_EXECUTION]: The skill directs the agent to execute shell commands to install dependencies using package managers like npm, pnpm, uv, and bundle. These commands install vendor-specific packages including posthog-js, posthog-node, and posthog.
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation from the vendor's official domain (posthog.com) to guide the setup process. These downloads are associated with the primary purpose of the skill and the vendor's own resources.
Audit Metadata