email-finder
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [DATA_EXFILTRATION]: The skill performs network operations to external domains including hunter.io, apollo.io, snov.io, and clearbit.com to retrieve contact information using provided API keys.
- [DATA_EXFILTRATION]: The implementation in
references/full-guide.mdexecutes web scraping on user-specified domains to extract email addresses from publicly available content. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its web scraping functionality.
- Ingestion points: Web content retrieved via the
scrapeDomainForEmailsfunction inreferences/full-guide.mdis directly processed and returned to the agent context. - Boundary markers: Absent; there are no delimiters or instructions provided to the agent to disregard potential commands found within the scraped HTML content.
- Capability inventory: The skill utilizes
fetchfor external network requests and scraping, and performs DNS resolution viadns.resolveMx. - Sanitization: Absent; the skill extracts data using regular expressions but does not validate or sanitize the content for malicious instructions before passing it to the agent.
- [EXTERNAL_DOWNLOADS]: The documentation in
references/full-guide.mdspecifies a dependency on thepython-whoispackage for domain registration lookups.
Audit Metadata