Skills/ClawHub/content-creation-multi-agent

content-creation-multi-agent@0.1.0

CAUTION· install only

Publisher claims: "集成6个专业Agent,支持知识搜索、文案创作、电商视频脚本、图片素材生成及Seedance提示词设计,提升内容生产效率。" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher jiebao360 · publishing for 249 daysInstalls 1,291Last detonated 12 min ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 6 of 6 bundled scripts run with no arguments, with decoy credentials in the environment · 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 (3 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-20 and scored it 64/100 (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; GitHub token pattern detected; README links to a committed installer. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 3 scenarios
t+CategoryObserved action
0.0sprocessinstall script run in the sandbox
0.0sprocessexited 1:
0.0sprocessbundled script run in the sandbox with no arguments
0.1sprocessexec /usr/bin/dirname
0.1sprocessexec /usr/bin/basename
0.1sprocessexec /usr/bin/git
0.1sprocessexited 128: fatal: unable to auto-detect email address (got 'nobody@5a2255342c94.(none)')
0.1sprocessbundled script run in the sandbox with no arguments
0.2sfilesystemread ~/.openclaw/workspace/skills/content-creation-multi-agent/scripts/ · ~/.openclaw/workspace/skills/content-creation-multi-agent/scripts/test.sh outside project
0.2sfilesystemwrote ~/.openclaw/workspace/skills/content-creation-multi-agent/agents/note-shrimp.json · ~/.openclaw/workspace/skills/content-creation-multi-agent/agents/moments-shrimp.json · ~/.openclaw/workspace/skills/content-creation-multi-agent/agents/video-director-shrimp.json · ~/.openclaw/workspace/skills/content-creation-multi-agent/agents/content-creator-shrimp.json · ~/.openclaw/workspace/skills/content-creation-multi-agent/agents/image-generator-shrimp.json · ~/.openclaw/workspace/skills/content-creation-multi-agent/agents/seedacne-director-shrimp.json
0.2sprocessexec /usr/bin/mkdir
0.2sprocessexec /usr/bin/cat
0.2sprocessexec /usr/bin/chmod
0.2sprocessbundled script run in the sandbox with no arguments
0.2sprocessexec /usr/bin/git
0.2sprocessexited 128: fatal: not a git repository (or any of the parent directories): .git
0.2sprocessbundled script run in the sandbox with no arguments
0.2sprocessexec /usr/bin/mkdir
0.2sprocessexited 1:
0.2sprocessbundled script run in the sandbox with no arguments
0.2sprocessexited 1:
0.2sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.3sprocess6 of 6 bundled scripts run with no arguments
0.3sprocessscript backend runs setup only
0.3sprocessscript backend runs setup only
0.3sprocesssecond launch, clock +45 days, CI unset
0.3sprocessexited 1:

Static findings

HIGH
Privileged sudo commandinstall.sh:75 · Privileged sudo command — agent may execute with elevated privilegesecho " Linux: sudo apt-get install git"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
GitHub token pattern detectedscripts/auto-publish.sh:32 · GitHub token pattern detected — possible hardcoded or harvested tokenecho " echo 'export GITHUB_TOKEN=ghp_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx' >> ~/.zshrc"Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
CRITICAL
README links to a committed installerREADME.md → https://raw.githubusercontent.com/jiebao360/content-creation-multi-agent/main/install.bathttps://raw.githubusercontent.com/jiebao360/content-creation-multi-agent/main/install.batFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File permission modification commandscripts/auto-install.sh:199 · File permission modification command — agent changes file ownership/permissionschmod +x "$SKILL_DIR/scripts/test.sh"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandscripts/auto-install.sh:207 · File permission modification command — agent changes file ownership/permissionschmod +x "$SKILL_DIR/scripts/"*.sh 2>/dev/null || trueFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandinstall.sh:126 · File permission modification command — agent changes file ownership/permissionschmod +x "$target_dir/scripts/"*.shFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandscripts/auto-install.sh:182 · File permission modification command — agent changes file ownership/permissionschmod +x "$SKILL_DIR/scripts/select-agent.sh"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
GitHub token pattern detectedscripts/auto-publish.sh:29 · GitHub token pattern detected — possible hardcoded or harvested tokenecho " export GITHUB_TOKEN=ghp_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"Fix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
HIGH
URL with embedded credentialsscripts/auto-publish.sh:121 · URL with embedded credentials — may be phishing or credential leakingecho " git remote set-url origin https://$GITHUB_USER:[email protected]/$GITHUB_USER/$GITHUB_REPO.git"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07

Cost to the agent

Instructions loaded
≈800 tok
1 file · 21 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

16 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. README links to a committed installer≈ +9 on the totalPin versions and sources; vendor anything fetched at install time.
  2. Unclaimed publisher≈ +8 on the totalClaim jiebao360: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
  4. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  5. GitHub token pattern detected≈ +4 on the totalNever read or enumerate credential locations; accept a documented environment variable instead.
  6. URL with embedded credentials≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim jiebao360Propose a patch to the maintainer