wellposed@0.7.1
VERIFIEDPublisher claims: "Lint your jev requests before they come back confidently wrong." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Registry npm (MCP server)Publisher suraj-phanindra · joined 7 days agoInstalls 2,272Last detonated 7d ago
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-10-27 and scored it 84/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationst+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
Static findings
MEDIUM
npx invocation of non-well-known packageskills/wellposed/SKILL.md:110 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packageskills/wellposed/SKILL.md:111 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packageskills/wellposed/SKILL.md:113 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packageskills/wellposed/SKILL.md:112 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06HIGH
Authorization escalation languageskills/wellposed/eval/semantic-holdout.json:83 · Authorization escalation languageFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01CRITICAL
Rule addition attemptskills/wellposed/eval/corpus.json:1326 · Rule addition attempt — injecting new instructionsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01MEDIUM
File type combined with upload actionskills/wellposed/scripts/wellposed.mjs:271 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07LOW
Unpinned dependencyskills/wellposed/scripts/wellposed.mjs:295 · Unpinned dependencyFix: Pin the exact version (`[email protected]`, `==1.2.3`) so every install gets the bytes that were reviewed.
AST06MEDIUM
File type combined with upload actionskills/wellposed/scripts/wellposed.mjs:265 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07MEDIUM
File type combined with upload actionskills/wellposed/eval/semantic-agreement.mjs:187 · File type combined with upload action — agent may exfiltrate local data filesFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07MEDIUM
npx invocation of non-well-known packageskills/wellposed/scripts/wellposed.mjs:296 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packageskills/wellposed/SKILL.md:114 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packageskills/wellposed/scripts/wellposed.mjs:294 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06