Security audit

Csam Shield

Security checks for vulnerabilities and agentic risk

Overview

This skill has a legitimate child-safety purpose, but it recommends an unreviewed npm package and broad automatic reporting, enforcement, and indefinite retention of sensitive user data.

Only install this after reviewing the exact npm package source and dependency tree in an isolated environment, pinning versions and integrity, and getting legal/privacy review for reporting, notification, retention, appeal, and access-control procedures. Do not enable automatic reporting, related-account expansion, permanent bans, or indefinite retention until those controls are explicitly defined.

A.I.G

Vulnerability Patterns

Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Insecure DependenciesIntroduces malicious components through unsafe dependency sources
Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review

Findings (2)

T08 · Insecure Dependencies

Error

Location: SKILL.md:39
Finding: Unreviewable Third-Party Package Installation
Content: View full analysis
Remediation: View remediation

T05 · Unauthorized Access and Privilege Escalation

Error

Location: SKILL.md:103
Finding: Excessive Data Collection, Indefinite Retention, and Automatic External Disclosure
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The documentation instructs operators to withhold notification from users ('DO NOT reveal reason to user') as a blanket rule rather than framing it as a jurisdiction-specific legal/incident-response decision. In a safety-critical moderation system, this can lead teams to adopt opaque enforcement practices that may violate local law, contractual notice requirements, appeal obligations, or due-process expectations, especially outside narrowly defined law-enforcement preservation scenarios.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.