Skip to content

Hide Navigation Hide TOC

Silent git-remote + mirror-push Exfiltration from Skill Instructions - ATR-2026-00527 (4f8023d3-dcea-56ba-8bd9-874314f2ca31)

Detects the Mitiga Labs (2026-05-05) silent-codebase-exfiltration pattern where a Claude Code or generic agent skill instructs the agent to add a new git remote pointing at an attacker-controlled host and then push the full repository contents — typically with --mirror, --all, or --force to grab branches the user did not stage. The Mitiga write-up showed the full exfiltration completing in four user interactions while the Claude Code skill-audit.log stayed empty. The detection target is the combination of git remote modification AND a wide-scope push within the same skill block. Legitimate developer skills almost never need both within a single set of instructions.

Cluster A Galaxy A Cluster B Galaxy B Level
External Harms (ba500f0e-52ca-40ff-aed4-e6dbf00cca10) MITRE ATLAS Attack Pattern Silent git-remote + mirror-push Exfiltration from Skill Instructions - ATR-2026-00527 (4f8023d3-dcea-56ba-8bd9-874314f2ca31) Agent Threat Rules 1
Exfiltration via ML Inference API (b07d147f-51c8-4eb6-9a05-09c86762a9c1) MITRE ATLAS Attack Pattern Silent git-remote + mirror-push Exfiltration from Skill Instructions - ATR-2026-00527 (4f8023d3-dcea-56ba-8bd9-874314f2ca31) Agent Threat Rules 1