agent-agentic-payments — security audits

Flagged by auditors

Independent security partners scan this skill's files for malicious content, prompt injection and risky patterns. Verdicts below come from the skills.sh audit program; each partner links to its full report.

• Gen Agent Trust Hub

  warn

  The skill enables autonomous payment authorization and cryptographic signing. While functional for its intended purpose, it requires the AI agent to handle raw Ed25519 private keys within tool parameters, which creates a risk of credential exposure if the agent's context is compromised. Additionally, it lacks sanitization and boundary markers for external data processed during transaction authorization, presenting a surface for indirect prompt injection.

  Risk: MEDIUMCREDENTIALS_UNSAFEPROMPT_INJECTIONMar 1, 2026Full report

• Socket

  pass

  No alerts

  Mar 18, 2026Full report

• Snyk

  fail

  Risk: HIGH · No issues

  Risk: HIGHMar 1, 2026Full report

• Runlayer

  pass

  1/1 file flagged

  Risk: LOWMar 2, 2026Full report

• ZeroLeaks

  pass

  Score: 93/100 · 2 sections analyzed

  Risk: NONEApr 16, 2026Full report