ecosystem-intake

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md:12-14 describes runtime ingestion of upstream GitHub/web content (e.g., via web_fetch or GitHub MCP get_file_contents) from outsider-authored repositories/lists, which would be read as free-form text and fed into the agent’s LLM context for triage.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs runtime fetching of external GitHub content (e.g., "hesreallyhim/awesome-claude-code" via github-mcp-server-get_file_contents or web_fetch) which would be ingested into the agent's prompts/context and thus directly influences its behavior.