buried-injections
🛡️ Regex catches 0%, Meta's Prompt Guard 2 catches 1% of 629 realistic AgentDojo injection attacks when they're buried in tool output. Reproducible benchmark.
Details
- External ID
- 1383910866
- Source
- GITHUB
- Company
- —
- Product
- buried-injections
- Website domain
- github.com
- Launched
- Sept. 23, 2026
- Cohort
- —
- Upvotes
- 19
- Upvotes percentile
- 0.5840379195490648
- Tags
- agentdojo, ai-agents, benchmark, llm-security, mcp, prompt-guard, prompt-injection
- Fetched at
- Sept. 27, 2026, 5:02 p.m.
- Updated at
- Sept. 27, 2026, 5:02 p.m.
Enrichment
- Theme
- proxy, dns, and networking tools
- Vertical
- Security
- Function
- Observability & eval
- Audience
- Developer
- AI stance
- AI feature
- Project type
- Hobby / open-source project
- Normalized one-liner
- benchmark for prompt injection attacks hidden in tool outputs
- Manually corrected
- False
Could you build this?
Yes It is an evaluation benchmark dataset and test runner script for evaluating LLM prompt injection defenses against tool outputs, easily created with Python and standard LLM APIs.
Competitors
Other products that read as similar to this one — 31 launches clear the similarity bar, closest 8 shown.
Attention rank: #12 of 32 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 245 days after the earliest competitor.
- Prompt-injection firewall for OpenClaw agents · hn · 2026-02-02 · 6 upvotes · similarity 0.41
- FireClaw · hn · 2026-03-17 · 5 upvotes · similarity 0.38
- Agent Arena · hn · 2026-02-06 · 47 upvotes · similarity 0.38
- SentinelAgent Guard · ph · 2026-09-23 · 2 upvotes · similarity 0.37
- Caveman · ph · 2026-08-13 · 160 upvotes · similarity 0.35
- Alovia · ph · 2026-09-29 · 1 upvotes · similarity 0.35
- BotShield · ph · 2026-09-12 · 2 upvotes · similarity 0.35
- jev-security-scan · github · 2026-09-19 · 10 upvotes · similarity 0.34
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a observability & eval tool for Media & entertainment yet.