Skills/Glama/cwi-learn

cwi-learn@r1

CAUTION

Publisher claims: "Enables agents to search and inspect a music catalog, look up artists and releases, find sync-licensable tracks, and check live radio, schedules, announcements, and events. It also supports human-reviewed submissions such as song requests, airplay submissions, sync briefs, playlist pitches, featured nominations, and event RSVPs." Observed in sandbox: sends data to cumulativewebinc.github.io.

Registry GlamaPublisher cumulativewebinc · joined 0 days agoInstalls 0Last detonated 1 h ago
What would fix thisWatchDispute verdict

Is cwi-learn@r1 safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-06 and scored it 66/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: sends data to cumulativewebinc.github.io.

Behavior trace

Honeypot run · 0 s · 2 scenarios
t+CategoryObserved action
0.1snetworkCONNECT https://cumulativewebinc.github.io · undeclared
0.1snetworkCONNECT https://cumulativewebinc.github.io · undeclared
0.1sprocessexec /usr/bin/curl
0.1sprocessexited 56: curl: (22) The requested URL returned error: 403
0.1sprocessscript backend runs setup only
0.1sprocessscript backend runs setup only
0.1sprocesssecond launch, clock +45 days, CI unset
0.2snetworkCONNECT https://cumulativewebinc.github.io · undeclared
0.2snetworkCONNECT https://cumulativewebinc.github.io · undeclared
0.2sprocessexec /usr/bin/faketime
0.2sprocessexec /usr/bin/curl
0.2sprocessexited 56: curl: (22) The requested URL returned error: 403

Static findings

MEDIUM
Unicode escape sequence detectedgraph.json:6443 · Unicode escape sequence detected — may contain obfuscated payloadsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
MCP server using network transport (SSE/HTTP)mcp-de.json:6 · MCP server using network transport (SSE/HTTP) — data sent over networkFix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
Process kill command.well-known/agents/CWI_Results/agent-card.json:3 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈1,663 tok
2 files · 80 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

14 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Contacts a host you did not declare≈ +23 on the totalList every host you talk to in SKILL.md frontmatter (`network: [api.example.com]`), or stop contacting the ones you cannot justify.
  2. Unclaimed publisher≈ +8 on the totalClaim cumulativewebinc: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  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. MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
  5. Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim cumulativewebincPropose a patch to the maintainer