Skills/ClawHub/agent-registry

agent-registry@2.0.1

CAUTION· static only

Publisher claims: "MANDATORY agent discovery system for token-efficient agent loading. Claude MUST use this skill instead of loading agents directly from ~/.claude/agents/ or ...." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher matrixy · publishing for 279 daysInstalls 4,444Last detonated 36 min ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-22 and scored it 63/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

MEDIUM
File type combined with upload actionbin/init.js:222 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(colorize(" Invalid input. Please enter numbers separated by commas.", C.red));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Unicode escape sequence detectedbin/init.js:350 · Unicode escape sequence detected — may contain obfuscated payloads… by lazy-loading agents \u2551", C.header)); console.log(colorize("\u255a\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u25…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
File type combined with upload actionbin/get.js:102 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(" --json Output as JSON with metadata");Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionbin/get.js:138 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(formatJsonOutput(agent, content));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File permission modification commandinstall.sh:78 · File permission modification command — agent changes file ownership/permissionschmod +x "$INSTALL_DIR/bin/"*.jsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known packageSKILL.md:77 · npx invocation of non-well-known package — may execute untrusted codenpx skills add MaTriXy/Agent-Registry@agent-registryFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionbin/list.js:99 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(" --json Output as JSON");Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionbin/get.js:140 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(formatAgentOutput(agent, content, rawOutput));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Unicode escape sequence detectedbin/init.js:347 · Unicode escape sequence detected — may contain obfuscated payloads…lp(); process.exit(options.invalid ? 1 : 0); } console.log(colorize("\n\u2554\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550…Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Access to sensitive file pathstests/registry.test.js:51 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesconst result = resolveRegistryAgentPath("../../etc/passwd");Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commandinstall.sh:80 · File permission modification command — agent changes file ownership/permissionschmod +x "$INSTALL_DIR/hooks/"*.jsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File type combined with upload actionbin/search-paged.js:160 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(formatResults(paginated, jsonOutput));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packageSKILL.md:80 · npx invocation of non-well-known package — may execute untrusted codenpx skills findFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:83 · npx invocation of non-well-known package — may execute untrusted codenpx skills updateFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionbin/get.js:103 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(" --raw Output raw content without headers");Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈2,433 tok
2 files · 26 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

17 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim matrixy: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  3. Unicode escape sequence detected≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
  4. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
  5. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  6. Access to sensitive file paths≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim matrixyPropose a patch to the maintainer