Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web
Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks.
[dsh-plugin.org | dsh-plugin-hub] plugin install failed: toby-bridges/api-relay-audit
[dsh-plugin.org | dsh-plugin-hub] plugin distribution incomplete: toby-bridges/api-relay-audit
bug: false positives in prompt extraction (Unicode apostrophe + refusal language)
Research: reproduce and validate single-token model fingerprinting