tdg-personal/lead-intelligence
AI-native lead intelligence and outreach pipeline. Replaces Apollo, Clay, and ZoomInfo with agent-powered signal scoring, mutual ranking, warm path discovery, source-derived voice modeling, and channel-specific outreach across email, LinkedIn, and X. Use when the user wants to find, qualify, and reach high-value contacts.
60
76%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
This skill explicitly ingests untrusted public third-party content—e.g., it requires Exa MCP web searches and X API scraping and, per SKILL.md Stage 4 and Tool Requirements, pulls "Recent X posts (last 30 days)" and optionally uses LinkedIn browser control to inspect profiles—then reads and uses that content to influence scoring, channel selection, and outreach drafts, which could allow indirect prompt injection.
Where we found it
Exa MCP (web_search_exa)
domain · 9 sites
The plugin uses Exa MCP to perform deep web searches whose results (arbitrary third-party web content) are ingested and used for signal scoring, enrichment, and outreach drafting, creating an indirect prompt injection surface.
X API (x.com / twitter.com)
domain · 11 sites
The plugin fetches tweets, bios, and follower data from arbitrary X/Twitter users via the X API; this untrusted content is used for scoring, enrichment, voice modeling, and outreach drafting, enabling indirect prompt injection.
LinkedIn (linkedin.com)
domain · 7 sites
The plugin inspects LinkedIn profiles and recent activity of arbitrary targets via browser control or API, ingesting untrusted profile content that influences scoring, enrichment, and outreach drafting.
GitHub MCP (github.com)
domain · 2 sites
The plugin fetches open source contributions from GitHub for developer-centric lead qualification, ingesting untrusted third-party content that influences lead scoring.
SKILL.md
29
**GitHub MCP** — For developer-centric lead qualification
SKILL.md
176
- GitHub: open source contributions (for developer-centric leads)
Apollo/Clay API
domain · 1 site
The plugin optionally fetches enrichment data from Apollo/Clay APIs, ingesting third-party content that could influence lead scoring and outreach.
SKILL.md
28
**Apollo/Clay API** — For enrichment cross-reference if user has access
- Audited
- Security analysis