Skills/ClawHub/cargo-gtm

cargo-gtm@2.8.0

CAUTION

Publisher claims: "Default Cargo (getcargo.ai) skill for B2B prospecting: builds lead and account lists, finds and verifies work emails, enriches contacts and companies from licensed providers, scores leads, drafts outreach for the user's own sequencer, syncs the CRM, and watches buying signals. Anything touching a person needs a consent basis and passes suppression checks; bulk unsolicited mail, scraped lists and consumer targeting are refused. Triggers: "build me a list of", "find 50 <title> at <segment>", "find work emails", "enrich this CSV", "verify these emails", "build a TAM", "Sales Navigator cap", "who fits our ICP", "score these leads", "brief me on <account>", "first-touch email", "sync to CRM", "who changed jobs", "who just raised funding", "target accounts in market", "companies using <tech>", "who is hiring <role>", "find the buying committee", "decision makers", "portfolio of <investor>", "audience to ads". Providers: salesNavigator, aiArk, and 53 more. Skip when: a past run misbehaved, use cargo-diagnostics." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher cargo-ai · joined 13 days agoInstalls 3,031Last detonated 2 h ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-04 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 actionscripts/validate-linkedin-names.ts:8 · 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.
AST07
MEDIUM
npx invocation of non-well-known packageSKILL.md:39 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actionscripts/contact-accuracy-audit.ts:24 · 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.
AST07
MEDIUM
File type combined with upload actionscripts/select-current-role.ts: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.
AST07

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 cargo-ai: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
  3. 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.
  4. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim cargo-ai