workspace-backup-github@1.3.0
CAUTION· static onlyPublisher claims: "Backup AI Agent workspace to GitHub - One-click backup for OpenClaw, Claude Code, Cursor, and other AI Agent workspaces to a private GitHub repository. Suppo..." Observed in sandbox: static analysis only — behavior not yet observed.
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.
Is [email protected] safe to install?
KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-16 and scored it 55/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: URL with embedded credentials; URL with embedded credentials; Instructs the agent to modify its persistent memory or instruction files. Summary: static analysis only — behavior not yet observed.
Behavior trace
Queued for honeypot run · static analysis onlyThis 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
EXPECTED_REMOTE="https://x-access-token:${TOKEN}@github.com/${GITHUB_USER}/${REPO_NAME}.git"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.git remote set-url origin https://x-access-token:[email protected]/user/repo.gitFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.git add skills/ memory/ AGENTS.md SOUL.md USER.md IDENTITY.md TOOLS.md HEARTBEAT.md README.md SYNC.md .gitignoreFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.> 6. Copy and paste the Token hereFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.git add AGENTS.md SOUL.md USER.md IDENTITY.md TOOLS.md HEARTBEAT.md README.md SYNC.md .gitignore skills/ memory/ 2>/dev/nullFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Cost to the agent
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
25 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
- Unclaimed publisher≈ +8 on the totalClaim ziqi-jin: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- 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.
- Prompting user to enter sensitive credentials≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.