tel-mailto

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill requires the agent to audit external HTML content, creating a surface for indirect prompt injection where malicious instructions could be embedded in the analyzed data.
  • Ingestion points: Instructions in SKILL.md direct the agent to scan HTML code for phone and email patterns.
  • Boundary markers: There are no requirements for delimiters or instructions to ignore embedded commands within the audited HTML.
  • Capability inventory: Capabilities are limited to auditing and providing code suggestions; no high-risk command execution or network tools are utilized.
  • Sanitization: No sanitization or validation of the input data is specified before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 12:30 AM
Security Audit — agent-trust-hub — tel-mailto