toby-bridges / api-relay-audit
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
Why this job: says: prompt injection; topics: ai-security, llm-security, prompt-injection
What it does
- It does not certify that a relay is safe.
- It does not replace manual security review or operational monitoring.
- It does not treat inconclusive as clean; blocked probes and ambiguous responses stay visible in the report.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 14 days ago
- Stars
- 909
- +5 this week
- Licence
- AGPL-3.0
- Share-alike, even hosted
- Downloads for
- None listed
- No release files
- Latest version
- v2.5.0
- Released 31 days ago
- Built with
- Python
- 92% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 48% closed
- 13 still open
- Pull requests
- 61 merged
- 16 waiting
- Releases
- 4
- 4 in the last year
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| NVIDIA / SkillSpector | 25,104 | yesterday | Apache-2.0 | No downloads |
| hashgraph-online / hol-guard | 1,081 | today | Apache-2.0 | Mac, Linux |
| uber / ADR | 2,128 | 25 days ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 92%
- JavaScript 8%
- Shell <1%
Topics
- ai-agents
- ai-security
- anthropic
- api-gateway
- claude
- llm-proxy
- llm-security
- openai-api
- prompt-injection
- python
- security-audit
- security-scanner
Project record
- JobAI security
- StatusListed
- Commits178
- Forks83
- Watching1
- Stars in 28 days+32
- CreatedMar 30, 2026
- First seen by usNov 7, 2026
- CheckedNov 10, 2026