ic-signal

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow calls anonymous public MCP tools (ic_signal_get_issue, ic_signal_get_story, ic_signal_search) that return full issue/story text and snippets from Immersive Commons’ public newsletter, which is outsider-authored free text ingested into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill performs runtime calls to https://www.immersivecommons.com/api/mcp and fetches per-issue content from https://www.immersivecommons.com/newsletter/{slug}.md which are ingested as raw context for LLM prompts (RAG), so remote content directly controls the agent's prompt/context.