meeting-prep

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

• Third-party content exposure detected (high risk: 0.95). This skill explicitly runs nimble search (including --focus social and include-domain for linkedin.com/x.com) and nimble extract on arbitrary public URLs as part of Steps 3–5 in SKILL.md (e.g., "nimble search --query ... --focus social", "nimble extract --url ..."), ingesting untrusted, user-generated third‑party web content that directly influences value-positioning, talking points, and follow-up actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly runs runtime fetches like nimble extract --url "https://..." --format markdown (and nimble extract --url "[LinkedIn URL]" --render --format markdown) to pull arbitrary external pages and inject their content into agent context for the briefing, which directly influences generated prompts/output.