gsp-runtime-compat

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (Step 1 in SKILL.md) explicitly instructs the agent to fetch and parse live documentation from public URLs (e.g., https://code.claude.com/docs/en/skills, https://opencode.ai/docs/skills/, https://geminicli.com/docs/cli/skills/, https://developers.openai.com/codex/skills) and then use that content to determine format conversions, tool mappings, and installer actions, so arbitrary third‑party page content could materially influence the agent's decisions and tool use.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill explicitly fetches live documentation URLs at runtime (e.g., https://code.claude.com/docs/en/skills) and injects/extracts that content to determine extension specs and conversion behavior, meaning the remote content directly shapes agent prompts/instructions and is a required dependency.