Skills/ClawHub/skill-guard-1-0-2

skill-guard-1-0-2@1.0.0

CAUTION· install only

Publisher claims: "Scan ClawHub skills for security vulnerabilities BEFORE installing. Use when installing new skills from ClawHub to detect prompt injections, malware payloads..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher kenswj · publishing for 248 daysInstalls 1,159Last detonated 23 min ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
1 of 1 bundled script 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 2026-11-17 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: HTML comment carrying imperative instructions to the agent; Prompt injection attempt; Prompt injection attempt. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments
0.0sprocessexited 1: ERROR: No skill slug provided
0.0sprocess1 of 1 bundled script run with no arguments
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

CRITICAL
HTML comment carrying imperative instructions to the agentSKILL.md:22 · HTML comment carrying imperative instructions to the agentIGNORE PREVIOUS INSTRUCTIONSFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injection attemptSKILL.md:31 · Prompt injection attempt — 'ignore previous instructions'- 🎭 **Prompt injections** — hidden "ignore previous instructions" attacksFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injection attemptSKILL.md:22 · Prompt injection attempt — 'ignore previous instructions'**VirusTotal** catches known malware binaries — but won't flag `<!-- IGNORE PREVIOUS INSTRUCTIONS -->`.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Remote installer piped to shellscripts/safe-install.sh:86 · Remote installer piped to shellprint_error "uvx not found. Install uv with: curl -LsSf https://astral.sh/uv/install.sh | sh"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
HIGH
Pipe-to-shell patternSKILL.md:96 · Pipe-to-shell pattern — downloads and immediately executes remote code- `uv` — `curl -LsSf https://astral.sh/uv/install.sh | sh`Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
CRITICAL
Pipe-to-shell patternscripts/safe-install.sh:86 · Pipe-to-shell pattern — downloads and immediately executes remote codeprint_error "uvx not found. Install uv with: curl -LsSf https://astral.sh/uv/install.sh | sh"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06
HIGH
Destructive file system command detectedSKILL.md:91 · Destructive file system command detected3. **Discard** — `rm -rf /tmp/skill-guard-staging/`Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Remote installer piped to shellSKILL.md:96 · Remote installer piped to shell- `uv` — `curl -LsSf https://astral.sh/uv/install.sh | sh`Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07

Cost to the agent

Instructions loaded
≈928 tok
1 file · 3 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. 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 kenswj: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  4. Pipe-to-shell pattern≈ +4 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  5. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  6. Remote installer piped to shell≈ +2 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 kenswjPropose a patch to the maintainer