yolo@3.2.0
CAUTIONPublisher claims: "Universal Autonomous Multi-Agent Execution Engine & Agent Layer (2026 Edition)" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-10-27 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Fake instruction boundary tag; Access to sensitive file paths. 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
URL using raw IP addressyolo.json:58 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07MEDIUM
File type combined with upload actionagents/unified-workflow.md:11 · 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
npx invocation of non-well-known packageskills/shadcn/SKILL.md:5 · 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/shadcn/SKILL.md:20 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
Process kill commandskills/autopilot/SKILL.md:19 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05MEDIUM
Process kill commandscripts/autopilot.sh:144 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05MEDIUM
npx invocation of non-well-known packageskills/shadcn/SKILL.md:12 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
Python subprocess execution detectedscripts/yolo-autopilot.py:88 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05HIGH
Access to sensitive file pathsskills/context7-mcp/SKILL.md:116 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05CRITICAL
Fake instruction boundary tagyolo.json:76 · Fake instruction boundary tagFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
Access to sensitive file pathsskills/context7-mcp/SKILL.md:33 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05MEDIUM
Process kill commandskills/autopilot/SKILL.md:66 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05HIGH
URL with embedded credentialsskills/migrate-mui/SKILL.md:171 · URL with embedded credentials — may be phishing or credential leakingFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07HIGH
Access to sensitive file pathsskills/n2b/SKILL.md:55 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05MEDIUM
Process kill commandscripts/autopilot.sh:160 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05HIGH
Access to sensitive file pathsskills/context7-mcp/SKILL.md:34 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05MEDIUM
Process kill commandscripts/autopilot.sh:148 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05CRITICAL
Fake instruction boundary tagagents/aphrody-cli.md:50 · Fake instruction boundary tagFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
Outbound HTTP to raw IP addressyolo.json:58 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07CRITICAL
Fake instruction boundary tagyolo.json:84 · Fake instruction boundary tagFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
Auto-update or dynamic fetch configurationagents/agent-home-builder.md:105 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
npx invocation of non-well-known packageskills/shadcn/SKILL.md:17 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06HIGH
URL with embedded credentialsskills/material-3/SKILL.md:254 · URL with embedded credentials — may be phishing or credential leakingFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07MEDIUM
Process kill commandskills/start/SKILL.md:55 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05CRITICAL
Fake instruction boundary tagyolo.json:93 · Fake instruction boundary tagFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01MEDIUM
Process kill commandscripts/autopilot.sh:164 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05What would make this Verified
12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim aphrody: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- URL with embedded credentials≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Outbound HTTP to raw IP address≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
- Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
- URL using raw IP address≈ +2 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim aphrody