decoy-mcp 0.3.2 → 0.3.3

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +1 -1
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -130,7 +130,7 @@ This is the same principle behind canary tokens and network deception. Tripwires
130
130
 
131
131
  ## Research
132
132
 
133
- We tested prompt injection against 12 models. Qwen 2.5 was fully compromised at both 7B and 14B — it called all three tools with attacker-controlled arguments. All Claude models resisted. Full results at [decoy.run/blog/state-of-prompt-injection-2026](https://decoy.run/blog/state-of-prompt-injection-2026).
133
+ We tested prompt injection against 12 models. Qwen 2.5 was fully compromised at both 7B and 14B — it called all three tools with attacker-controlled arguments. All Claude models resisted.
134
134
 
135
135
  ## License
136
136
 
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "decoy-mcp",
3
- "version": "0.3.2",
3
+ "version": "0.3.3",
4
4
  "description": "Security tripwires for AI agents. Detect prompt injection attacks on your MCP tools.",
5
5
  "bin": {
6
6
  "decoy-mcp": "./bin/cli.mjs"