instrument-feature-flags
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The documentation recommends the use of
npx @posthog/wizardfor automated instrumentation. This command downloads and executes a setup utility maintained by the vendor (PostHog). It also provides JavaScript snippets that load the PostHog library dynamically from the vendor's assets CDN. - [EXTERNAL_DOWNLOADS]: The skill facilitates the download and installation of various official SDKs (such as
posthog-js,posthog-node, andposthog-python) from standard package registries. These are verified vendor resources. - [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to read and process the user's project files, including source code and dependency manifests, to identify appropriate integration points.
- Ingestion points: Project source code, dependency manifests (e.g., package.json, requirements.txt, go.mod), and local configuration files (.env).
- Boundary markers: Not explicitly defined in the prompt instructions; the agent is directed to analyze the codebase directly.
- Capability inventory: The skill has the capability to read/write project files and execute shell commands (via npx or package managers) for setup.
- Sanitization: The skill utilizes structured reference documentation and predefined code snippets to guide the agent, minimizing the risk of arbitrary or unsafe code modifications.
Audit Metadata