anysite-vc-analyst

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

• Third-party content exposure detected (high risk: 0.90). The skill's required onboarding and analysis steps explicitly fetch and parse external webpages and documents—e.g., mcp__anysite__parse_webpage(url=website), WebFetch/Read for pitch decks, mcp__anysite__get_linkedin_profile, and WebSearch for fund portfolios—so it ingests untrusted public web and social content that can directly influence scoring and outreach decisions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill fetches and injects user-supplied external URLs at runtime — e.g., company website via mcp__anysite__parse_webpage(url=...), pitch deck via WebFetch(link), and LinkedIn via mcp__anysite__get_linkedin_profile(user="linkedin-url-or-username") — and that fetched content is directly used to control prompts and generate outputs, making these runtime dependencies a potential vector for malicious or manipulative content.