Skills/ClawHub/ask-cargo

ask-cargo@0.3.0

CAUTION· static only

Publisher claims: "Ask your go-to-market repo and workspace anything from Slack: one agent the whole team @mentions answers from context, cadence and live runs, turns change requests into pull requests, captures a thread worth keeping into the cadence log and context, and hands work to the other deployed agents only after a go in the thread. Triggers: "let the team ask our GTM agent from slack", "one agent on top of all the others", "a slack bot that knows our repo", "ask cargo from slack", "orchestrator agent for our GTM stack", "let anyone open a PR from slack", "capture this slack thread into our context". Cargo project, defineAgent, harness claudeCode, Slack connector trigger, GitHub, cargo-ai CLI. Skip when: you want the day recapped and posted to Slack on a schedule, which is standup; or you want an answer in this chat right now with nothing deployed." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher cargo-ai · publishing for 258 daysInstalls 591Last detonated 24 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.

What changed since 0.2.3

vet-skills diff ask-cargo 0.2.3 0.3.0

In the sandbox, this version reached for nothing 0.2.3 did not. Compared from the two recorded runs, not from source.

0.3.0 was not run in the sandbox (static only); the comparison covers what static analysis recorded only.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-16 and scored it 71/100 (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
npx invocation of non-well-known packageinfra/agents/ask-cargo.prompt.ts:57 · npx invocation of non-well-known package — may execute untrusted codeotherwise \`npx --yes @cargo-ai/cli\`. Start with \`cargo-ai whoami\`. If itFix: Pin versions and sources; vendor anything fetched at install time.
AST06

No other findings across 1,039 lines in 14 files.

Cost to the agent

Instructions loaded
≈5,997 tok
1 file · 14 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

9 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. 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-aiPropose a patch to the maintainer