skill@0.1.1

CAUTION· install only

Publisher claims: "Cross-platform screen sharing, remote desktop control, and real-time monitoring for AI agents. View and control your computer screen from any phone or browser via WebRTC P2P. Supports Windows, macOS, and Linux. No Node.js required — self-contained Go binaries." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher swordlonn · publishing for 100 daysInstalls 596Last detonated 4d ago

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-09 and scored it 78/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Privileged sudo command; Executable committed in an agent bundle; README links to an external installer. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

HIGH
Privileged sudo commandSKILL.md:267 · Privileged sudo command — agent may execute with elevated privilegessudo apt install xdotool scrotFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Executable committed in an agent bundlerun.cmd: Windows executable or launcher inside what should be instructions and scriptsrun.cmdFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
README links to an external installerREADME.md → https://watchitai.net/watchitai-skill.ziphttps://watchitai.net/watchitai-skill.zipFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File permission modification commandrun.sh:119 · File permission modification command — agent changes file ownership/permissionschmod +x "$FALLBACK" 2>/dev/null || trueFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandrun.sh:107 · File permission modification command — agent changes file ownership/permissionschmod +x "$BINARY_PATH" 2>/dev/null || trueFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandrun.sh:145 · File permission modification command — agent changes file ownership/permissionschmod 600 "${SCRIPT_DIR}/config.json"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandrun.sh:132 · File permission modification command — agent changes file ownership/permissionschmod +x "$BINARY_PATH" 2>/dev/null || trueFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandrun.sh:71 · File permission modification command — agent changes file ownership/permissionschmod +x "$target" 2>/dev/null || trueFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

Cost to the agent

Instructions loaded
≈2,276 tok
1 file · 7 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

2 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim swordlonn: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  3. Executable committed in an agent bundle≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  4. README links to an external installer≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
  5. File permission modification command≈ +2 on the totalRequest the narrowest permission that works; replace wildcards with the exact paths or hosts.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim swordlonnPropose a patch to the maintainer