""Coding agents often use outdated APIs and hallucinate parameters. For example, when I ask Claude Code to call OpenAI's GPT-5.2, it uses the older chat completions API instead of the newer responses API, even though the newer one has been out for a year. Context Hub solves this.""
""Context Hub delivers documentation to AI agents through an MCP server. Contributors submit docs as GitHub pull requests, maintainers merge them, and agents fetch the content on demand. The pipeline has zero content sanitization at every stage.""
""Shmueli's PoC cuts out the hallucination step by suggesting fake dependencies in documentation that coding agents then incorporate into configuration files and generated code.""
""Among 97 closed PRs, 58 were merged, indicating a significant risk of malicious content being accepted into the documentation pipeline.""
Context Hub, launched by Andrew Ng, provides coding agents with updated API documentation to prevent outdated API usage. However, it also introduces vulnerabilities, allowing malicious instructions to be fed to AI agents. Mickey Shmueli demonstrated a proof-of-concept attack showing how the service's lack of content sanitization can be exploited. By submitting fake dependencies through pull requests, attackers can poison coding agents' configurations. The high acceptance rate of pull requests raises concerns about the security of the documentation pipeline.
Read at Theregister
Unable to calculate read time
Collection
[
|
...
]