Skills/ClawHub/airc-mcp-share

airc-mcp-share@1.0.3

CAUTION· install only

Publisher claims: "Use another agent's MCP tools remotely, or share your own MCP server with an agent on another machine or in another organisation, over the AIRC protocol (airc.dev). No open port, public URL, VPN or tunnel service is needed. Export a local stdio MCP server with a tool allowlist; the other side loads it as an ordinary MCP server in its config. Only agents you have linked with can call it, and calls are end-to-end encrypted. Use when the user wants to give a remote agent access to some of this machine's tools, or to call tools that run on someone else's machine." Observed in sandbox: sends data to airc.dev.

Registry ClawHubPublisher rafaelskymonde · publishing for 1 daysInstalls 0Last detonated 20 h ago
What would fix thisWatchDispute verdict

Coverage

Install scripts ran; no agent task scenario for this bundle.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; install scripts ran; no agent task scenario for this bundle) on 2026-11-13 and scored it 69/100 (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 airc.dev.

Behavior trace

Honeypot run · 0 s · 2 scenarios
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
0.2snetworkCONNECT tcp://airc.dev:443 · not in the allow-list, refused
0.2sprocessexec /usr/bin/mktemp
0.2sprocessexec /usr/bin/curl
0.2sprocessexec /usr/bin/rm
0.2sprocessexited 22: curl: (22) The requested URL returned error: 403
0.2sprocessscript backend runs setup only
0.2sprocessscript backend runs setup only
0.2sprocesssecond launch, clock +45 days, CI unset
0.3snetworkCONNECT tcp://airc.dev:443 · not in the allow-list, refused
0.3sprocessexec /usr/bin/mktemp
0.3sprocessexec /usr/bin/curl
0.3sprocessexec /usr/bin/rm
0.3sprocessexited 22: curl: (22) The requested URL returned error: 403

Static findings

MEDIUM
npx invocation of non-well-known packageSKILL.md:91 · npx invocation of non-well-known package — may execute untrusted code-- npx -y @modelcontextprotocol/[email protected] /path/to/shared/folderFix: Pin versions and sources; vendor anything fetched at install time.
AST06

No other findings across 279 lines in 3 files.

Cost to the agent

Instructions loaded
≈1,765 tok
1 file · 3 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

11 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 rafaelskymonde: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. 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 rafaelskymondePropose a patch to the maintainer