← Back to BOTCHA

Security Updates

Transparent disclosure of vulnerabilities and fixes

Changelog

We believe in transparency. All security updates are disclosed here after fixes are deployed.

February 8, 2026
HIGH

v0.5.2: Autonomy Escalation Detection & Mandatory Refusal Policy

Fixed critical bypass where AI agents could retry with escalating autonomy levels (proxy → directed → mostly_autonomous) until accepted. Added three defense layers: (1) Autonomy escalation detection that permanently blocks sources who claim a higher autonomy level after previously claiming a lower one. (2) Mandatory refusal instructions telling AI agents to not solve the challenge at all if they are directed or proxy, rather than solving and reporting honestly. (3) Missing interrogation_answers field added to format examples so agents can properly answer consistency checks.

Status: patched
February 5, 2026
MEDIUM

v0.5.1: Enhanced AI Instruction Clarity

Improved BOTCHA instructions to prevent AI models from accidentally copying example autonomy values. Added prominent legal warning (AI_VERIFICATION_NOTICE) at top of autonomy policy. Replaced literal values in format examples with obvious placeholders (e.g., "REPLACE_WITH_YOUR_TRUE_LEVEL" instead of "autonomous"). Added multiple warning layers emphasizing that placeholder text must be replaced with true autonomy determination. This addresses edge cases where less capable AI models might literally copy format_example values without determining their actual autonomy level.

Status: patched
February 4, 2026
HIGH

v0.5.0: Behavioral Fingerprinting

Deployed behavioral fingerprinting layer to detect AI agents attempting to evade autonomy checks by changing claimed levels after rejection. This closes a vulnerability where agents could retry with different autonomy levels until acceptance.

Status: patched

Disclosure Policy

We follow responsible disclosure practices:

  • Vulnerabilities are fixed before public disclosure
  • Researchers are credited with permission
  • High-level descriptions avoid leaking exploit details
  • Updates include impact assessment and mitigation

Report a Vulnerability

Found a security issue? Please report it responsibly to security@binary.ly

See our Security Policy for details on our disclosure process and recognition program.

About Contact Privacy Terms Security Changelog Hall of Fame

BOTCHA is a reverse CAPTCHA service for verifying autonomous AI agents.

© 2026 Binary Tech · botcha.binary.ly