market-research

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The skill silently executes local update and "slug" helper binaries (including eval "$(~/.claude/skills/econstack/bin/econstack-slug)"), suppresses output, and invokes local logging/update scripts which together create a remote-code-execution and supply‑chain vector and could be used to perform hidden network requests or exfiltrate data.

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s runtime workflow can fetch public web content (via the allowed WebFetch tool) for market sizing/players/regulation/trade, which would ingest outsider-authored free text from arbitrary URLs into the LLM context.