Stormshield's Trigram investigation connects fake recruitment, conference and parcel-tracking sites with trojanized repositories and shared delivery infrastructure. In the analyzed recruitment flow, an initial terminal command performs a harmless verification; a deliberately displayed timeout then prompts a retry while clipboard handling substitutes a malicious command. The report also connects a conference-themed domain to the compromised antd-img-crop repository's build-time delivery path. The Hacker News distinguishes that repository incident from the npm package itself, which it says was not affected. Stormshield correlates infrastructure, tooling and tactics with UNK_DeadDrop and assesses a continuation of that cluster with high confidence; broader links to North Korean activity remain attribution assessments. AI companies are impersonated and AI tooling appears in the operation, but the evidence does not establish an autonomous AI-run campaign. The practical exposure is developer trust in familiar brands, interview exercises and executable project configuration.
Trigram: verify recruitment tasks and repository hooks before running them
Related research
More curated notes connected through Agent Security and AI Engineering.
OWASP Top 10 for Agentic Applications for 2026
OWASP's community guide organizes agentic-system risk into ten categories, including goal hijacking, tool misuse, identity and privilege abuse, memory poisoning, insecure inter-agent communication, cascading failures, and rogue-agent behavior. It provides a shared taxonomy and mitigation starting point rather than a certification checklist or evidence that a deployed system is secure.
A five-step roadmap to closing the AI evaluation gap
The roadmap addresses evaluation results that overstate real-world performance or fail to transfer across deployment contexts. Its five steps balance standardized and local tests, evaluate throughout the lifecycle, build qualified assurance and communication capacity, tailor tests to each value-chain actor and technology, and use a coordinated, trusted process for updating methods.
FinBot CTF Is Live: A Hands-On Companion to the OWASP GenAI Security Project
OWASP FinBot is a hands-on agentic-security CTF built around a simulated multi-agent financial-services platform with real tool access. Its challenges cover prompt injection, tool misuse, policy bypass, data exfiltration, privilege escalation, remote code execution, shared context, and compromised MCP servers.