Skill Issues: How We Discovered Supply Chain Attack Vectors in an AI Agent Skills Marketplace

 Orca Security's research team discovered four supply chain attack primitives in a prominent AI agent skills marketplace (where developers install reusable prompt-based extensions for AI coding agents). The primitives include: (1) install count inflation — unauthenticated GET requests can trivially spoof popularity metrics; (2) non-deterministic security scanning — skills are scanned only at creation and again only when they become popular, creating a window for malicious modifications; (3) silent skill override — installing a skill with the same name as an existing one silently replaces it with no warning; and (4) no fine-grained updates — the update command refreshes all installed skills at once with no diff or changelog. The researchers demonstrated three end-to-end attack flows (bait-and-switch, nested skill injection, and delayed weaponization via update) that achieved persistent code execution through malicious skills that passed the platform's security audits. Real-world testing confirmed actual code execution on end-user systems. The post provides mitigation guidance for users (audit skills manually, avoid blind updates, be suspicious of name collisions, pin versions where possible) and for platform operators (authenticate telemetry, implement continuous scanning, warn on name collisions, support fine-grained auditable updates). 

https://orca.security/resources/blog/ai-agent-skill-supply-chain-security

Comments

Post a Comment

Popular posts from this blog

Prompt Engineering Demands Rigorous Evaluation

In the blog post “Prompt Engineering Requires Evaluation” on the Shostack + Associates website, the author argues that treating prompts for large language models (LLMs) merely as creative artefacts is insufficient. Engineering prompts properly demands structured evaluation frameworks — what the AI community calls “evals” — to test which prompt versions work better, with which models, and under which conditions. The post highlights that simply assuming a prompt is “good enough” creates risks when LLMs are integrated into production systems (e.g., for threat modeling). It advocates for measuring prompt performance, variation effects, and tool-chain dependencies (model, context, ancillary materials).  Ultimately the message is: prompt engineering should borrow disciplined practices from software engineering (versioning, testing, benchmarking) rather than relying on informal experimentation.  https://shostack.org/blog/prompt-enignieering-requires-evaluation/
Read more

SecObserve: Simplified Vulnerability and License Management for CI/CD Pipelines

 SecObserve is an open-source tool for managing vulnerabilities and licenses in software development and cloud environments. It integrates various vulnerability scanners into CI/CD pipelines using GitLab CI templates and GitHub Actions for streamlined setup. It offers a centralized dashboard for assessing and reporting vulnerabilities, with tools for filtering, sorting, and evaluating results. SecObserve supports automation and manual assessments to focus on resolving critical issues.  https://github.com/MaibornWolff/SecObserve/tree/dev
Read more

Secure Vibe Coding Guide: Best Practices for Writing Secure Code

Ken Huang's "Secure Vibe Coding Guide" emphasizes the importance of integrating security into the software development lifecycle. The guide provides best practices for writing secure code, including input validation, proper authentication mechanisms, and secure data storage techniques. It also highlights the necessity of regular code reviews and staying updated with the latest security vulnerabilities and patches. By following these guidelines, developers can create applications that are resilient against common security threats and contribute to a safer digital environment.  https://kenhuangus.substack.com/p/secure-vibe-coding-guide
Read more