instrument-product-analytics

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to retrieve or ask for the PostHog project API key and write it into env files (or otherwise embed it into code/config), which requires the LLM to handle and output secret values verbatim.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill includes a client-side PostHog snippet that at runtime loads and executes remote JavaScript from the PostHog host (e.g., https://us.i.posthog.com/static/array.js), and the integration depends on that remote script to function.