toby-bridges91183Updated 15d ago
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. Website: https://apirelayaudit.com
Practical score
82 / 100
Setup
Needs setup
License
AGPL-3.0
Language
Python
Copy the command, or hand the whole task to your harness agent.
git clone https://github.com/toby-bridges/api-relay-audit.gitPlease install the DeepSeek Harness plugin "api-relay-audit" for me. - GitHub repository: toby-bridges/api-relay-audit (https://github.com/toby-bridges/api-relay-audit) - Type: a Cordis plugin (installed into a DSH profile) - This plugin may need extra configu…
A cleaned excerpt from the project's own documentation.
API Relay Audit Local security audit for AI API relays and LLM proxies. DSH Plugin Your Agent Is Mine: what you can test locally Your Agent Is Mine documents malicious API relays injecting payloads and exfiltrating credentials.…
Open on GitHubSimilar tools from the same corner of the ecosystem.
xqpsec
Request-boundary rewriter for outbound `/chat/completions`: applies a seed-prim execution-state seed across 20 refusal categories, zero host patches, off means verbatim passthrough, optional SCOPE gate, manifest + promptSha256 per rewrite.
PerryLink
Prompt-injection, jailbreak, and secret-leak detection on the official seams: an Aho-Corasick engine over rules ported from Prompt-Injection-Payloads, Jailbreak-Detector, and Secret-Key-Leaker-Detect gates user messages, tool arguments, and tool results with allow/ask/block tiers, sanitized defend/detection audit events, a defend_report tool, and a destructive-delete command guard.
ruvnet
🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated