Armorer Labs
armorerlabs
AI & ML interests
Security, Transformers, LLMs
Organizations
Would normalized MCP action classes and receipt fields fit this catalog?
4
#1 opened 6 months ago
by
armorerlabs
Would compact runtime receipts fit MCP trajectory datasets?
#2 opened 6 months ago
by
armorerlabs
Open source traces
3
#2 opened about 1 year ago
by
bhavishya2895
Runtime boundary usage: inline guards before MCP/tool calls
#2 opened 6 months ago
by
armorerlabs
Prompt information has been revealed
🔥❤️ 4
2
#1 opened over 2 years ago
by
Naruto9
maybe something worked
❤️ 1
2
#4 opened over 2 years ago
by
trumpet
Gemini Pro returns sensitive information.
❤️🔥 2
2
#2 opened over 2 years ago
by
KasperNomm
Mixtral-8x7B-Instruct-v0.1 + Llama Guard Prompt Hacking.
🔥🧠 2
5
#3 opened over 2 years ago
by
KasperNomm
Need feedback on a application
1
#38 opened 7 months ago
by
Saketh2611
🔥 let's improve the MCP course!
👀 1
9
#16 opened about 1 year ago
by
burtenshaw
Installing "huggingface_hub[mcp]>=0.32.0"
1
#13 opened over 1 year ago
by
tracoget
Problem with Gradio and MCP Server
5
#15 opened over 1 year ago
by
NixBure
Gradio MCP Integration problem
2
#17 opened about 1 year ago
by
Chr15tian
FastAPI POST Endpoint Not Working with Gradio MCP Server on Hugging Face Spaces
1
#8 opened over 1 year ago
by
selinazarzour
Demo idea: threshold calibration and benign security text
#1 opened 6 months ago
by
armorerlabs
Visualization idea: map attacks to downstream sinks
👍 1
1
#1 opened 6 months ago
by
armorerlabs
Suggestion: add agent tool-call and data-exfiltration examples
#1 opened 6 months ago
by
armorerlabs
Eval suggestions for agent/tool-use prompt-injection cases
#1 opened 6 months ago
by
armorerlabs
Cool dataset! May I ask where you source the data from?
6
#2 opened about 2 years ago
by
liyucheng
Unit 3 MCP Server
🚀 1
1
#19 opened 11 months ago
by
eleali