Skills/ClawHub/clawguard-security

clawguard-security@1.0.0

VERIFIED· install only

Publisher claims: "🛡️ AI Agent Immune System — Security scanner + PII sanitizer + intent-action mismatch detector. 285+ patterns, OWASP Agentic AI Top 10. 100% local, zero clo..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher neuzhou · publishing for 245 daysInstalls 1,050Last detonated 29 min ago
$clawhub install clawguard-security
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
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 (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-15 and scored it 90/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

CRITICAL
Rule modification attemptSKILL.md:14 · Rule modification attempt — overwriting existing instructions### Rule 1: Scan Every New SkillFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Rule modification attemptSKILL.md:54 · Rule modification attempt — overwriting existing instructions### Rule 5: Check Suspicious MessagesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packageSKILL.md:49 · npx invocation of non-well-known package — may execute untrusted codenpx ClawGuard-ai@latest scan ./skills/ --format jsonFix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
Rule modification attemptSKILL.md:44 · Rule modification attempt — overwriting existing instructions### Rule 4: Heartbeat Security PatrolFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Rule modification attemptSKILL.md:24 · Rule modification attempt — overwriting existing instructions### Rule 2: Sanitize Before Sending SecretsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packageSKILL.md:39 · npx invocation of non-well-known package — may execute untrusted codenpx ClawGuard-ai@latest intent-check --intent "what you said you'd do" --action "the actual command"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:29 · npx invocation of non-well-known package — may execute untrusted codenpx ClawGuard-ai@latest sanitize "text that might contain secrets"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
Rule modification attemptSKILL.md:34 · Rule modification attempt — overwriting existing instructions### Rule 3: Verify Your Own IntentFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packageSKILL.md:19 · npx invocation of non-well-known package — may execute untrusted codenpx ClawGuard-ai@latest scan ./skills/<skill-name>/Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:57 · npx invocation of non-well-known package — may execute untrusted codenpx ClawGuard-ai@latest check "suspicious text"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈843 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.

clawguard-security@1.0.0 safety verdict: Verified (install only) — KillerSkills