clay-core-workflow-b
Use Claygent AI research and AI-powered personalization to generate outreach copy from enriched data. Use when writing personalized email openers, running Claygent research prompts, or configuring AI columns for campaign personalization at scale. Trigger with phrases like "clay AI personalization", "claygent research", "clay outreach copy", "clay secondary workflow", "clay AI column".
85
83%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Risky
Do not use without reviewing
Security
2 findings — 1 high severity, 1 medium severity. You should review these findings carefully before considering using this skill.
W007: Insecure credential handling detected in skill instructions
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
Insecure credential handling detected (high risk: 0.80). The prompt's HTTP API example includes an Authorization header "Bearer {{Instantly API Key}}" and similar templated credential placeholders, which encourages embedding API keys directly into generated requests/configurations and could cause the LLM to emit secret values verbatim.
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
Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs Claygent to scrape and navigate arbitrary company domains and public sources (e.g., "Research {{Company Name}} ({{domain}})", checks of job postings, BuiltWith/Wappalyzer, Glassdoor, and Navigator mode visiting {{domain}}/pricing) and then uses that extracted, user-generated/untrusted content to drive AI-generated personalization and downstream actions, which could enable indirect prompt injection.
- Commit
70e9fa4
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.