gleap-sdk-setup

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly resolves API keys from the conversation, .env, or environment and instructs the agent to "add initialization code using the resolved API key" and offer to write it to .env, which requires the LLM to handle and often embed secret values verbatim in outputs/commands, creating an exfiltration risk.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.70). The skill runs scripts/get-latest-versions.sh which curl-fetches package metadata from public registries (registry.npmjs.org, search.maven.org, api.github.com, pub.dev, etc.), and the agent is expected to read and use those returned version strings in install commands, thereby ingesting untrusted third‑party content.