PG1 Sovereign Threat Intelligence
io.github.Project-Gifted1/pg1-threat-intel · v1.22.0 · score 57/100 · checked 2026-11-22
Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works
Preflight for AI agents, signed: one call; wallet, domain, IP abuse, package checks and CVEs.
Source: https://github.com/Project-Gifted1/pg1-ai-agent
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 22 tool(s) to anyone, no credentials needed. |
| Critical | MW101 | tool 'check_agent_message': description contains instruction-like text aimed at the model ('ignore previous instructions'). Possible tool poisoning. |
What was checked
- https://pg1-ai-agent.vercel.app/api/mcp: answers without auth
Public tools: preflight_check, check_x402_endpoint, check_agent_card, check_agent_message, check_repo_trap, verify_result, hosting_advisor, get_threat_indicators, get_cve_details, get_ioc_context, get_cve_batch, get_ioc_batch, get_threat_actor_profile, get_cve_by_product, get_usage_status, submit_indicator, check_wallet_sanctions, check_domain_age, check_hostname_reputation, check_wallet_age, check_ip_abuse, check_package
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-project-gifted1-pg1-threat-intel-75182cf2)