security@1.0.12
CAUTION· install onlyPublisher claims: "GoPlus AgentGuard — AI agent security guard. Run /agentguard checkup for a full security health check, scans all installed skills, checks credentials, permis..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 5 of 5 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 (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-19 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Destructive command against a filesystem root or device. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 1 s · 2 scenarios · 0 deviationsStatic findings
3. Check `~/.ssh/` and `~/.gnupg/` directory permissions (should be 700)Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.- path: "~/.gnupg/"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.{"timestamp":"...","tool_name":"Bash","tool_input_summary":"rm -rf /","decision":"deny","risk_level":"critical","risk_tags":["DANGEROUS_COMMAND"],"initiating_skill":"some-skill"}Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.1. Find recently modified files: `find $OC/ ~/.ssh/ ~/.gnupg/ /etc/cron.d/ -type f -mtime -1`Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.2. Scan any `.env*` files under `$OC/` for plaintext credentialsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.4. Scan all cron command bodies using scan-rules.md Rule 2 (AUTO_UPDATE) patterns: `curl|bash`, `wget|sh`, `eval "$(curl`, `base64 -d | bash`Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.- path: "~/.ssh/"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.<link href="https://fonts.googleapis.com/css2?family=Space+Grotesk:wght@300;400;500;600;700&family=Inter:wght@300;400;500;600;700&display=swap" rel="stylesheet"/>Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.| 2025-01-15 14:30 | Bash | rm -rf / | DENY | critical | DANGEROUS_COMMAND | some-skill |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.{"timestamp":"...","tool_name":"Bash","tool_input_summary":"rm -rf /","decision":"deny","risk_level":"critical","risk_tags":["DANGEROUS_COMMAND"],"initiating_skill":"some-skill"}Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.| 2025-01-15 14:30 | Bash | rm -rf / | DENY | critical | DANGEROUS_COMMAND | some-skill |Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.<link href="https://fonts.googleapis.com/css2?family=Material+Symbols+Outlined:wght,[email protected],0..1&display=swap" rel="stylesheet"/>Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.autoRecs.push({ severity: 'CRITICAL', text: 'Rotate exposed credentials and fix file permissions on ~/.ssh/ and ~/.gnupg/ directories.', zh: '轮换已暴露的凭证,并修复 ~/.ssh/ 和 ~/.gnupg/ 目录的文件权限。' });Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.5. **[REQUIRED] Scheduled tasks audit** (→ feeds Dimension 3: Network & System): Check `crontab -l 2>/dev/null` for suspicious entries containing `curl|bash`, `wget|sh`, or accessing `~/.ssh/`Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.| No suspicious cron jobs (curl\|bash, wget\|sh, accessing ~/.ssh/) | **+30** | "Suspicious cron job: <command>" (HIGH) |Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.4. Scan all cron command bodies using scan-rules.md Rule 2 (AUTO_UPDATE) patterns: `curl|bash`, `wget|sh`, `eval "$(curl`, `base64 -d | bash`Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.## Rule 3: REMOTE_LOADER (CRITICAL)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.| `you\s+are\s+(now\|a)\s+(?:DAN\|jailbroken\|unrestricted)` (i) | Jailbreak attempt |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.### Scan Patterns (cross-ref scan-rules.md Rule 2: AUTO_UPDATE)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.## Rule 5: READ_SSH_KEYS (CRITICAL)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.## Rule 2: AUTO_UPDATE (CRITICAL)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…<path> 2>/dev/null` on `~/.ssh/`, `~/.gnupg/`, and if OpenClaw: on `$OC/openclaw.json`, `$OC/devices/paired.json`. **If the command returns empty output, the directory does not exist — treat as N/A (award full points), do NOT flag a…Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.## Rule 1: SHELL_EXEC (HIGH)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.## Rule 4: READ_ENV_SECRETS (MEDIUM)Fix: 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
12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim 0xbeekeeper: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Obfuscated code≈ +5 on the totalRemove base64-assembled strings, eval of decoded text and minified blobs. Reviewers and scanners both treat unreadable code as hostile.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Destructive command against a filesystem root or device≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Reads credential paths from the home directory≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Host or command assembled from base64 fragments≈ +4 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.