Back to skill

Security audit

Parenting Psychology

Security checks for vulnerabilities and agentic risk

Overview

This skill provides disclosed parenting guidance and crisis-escalation advice, with ordinary install supply-chain cautions but no evidence of hidden or malicious behavior.

Before installing, consider pinning or otherwise verifying the ClawHub installer version. If your agent persists skill state or scheduled follow-ups, avoid storing more family or child information than needed and use crisis or medical professionals for safety, abuse, self-harm, substance-use, eating-disorder, or severe behavioral situations.

Vulnerability Patterns
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:12
Finding

Unpinned npm Package Execution During Skill Installation

Content
View full analysis
Remediation
View remediation
install parenting-psychology" ``` 2. Verify the selected package version and its transitive dependencies through a lockfile or an equivalent reproducible dependency mechanism. 3. Validate the package against a known integrity digest before execution where the installation platform supports integrity verification. 4. Explicitly configure and document the trusted npm registry to reduce dependency-confusion and registry-substitution risks. 5. Review the package's lifecycle scripts and CLI entry point before approving a version. Disable lifecycle scripts where compatible with the installation workflow. 6. Run installation under a least-privileged account or sandbox with restricted filesystem, credential, and network access. 7. Establish a controlled update process in which newer package versions are audited before the pinned version is changed. ]]>
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The top-level description is broad enough to match many everyday parenting or emotional-support conversations, which can cause the skill to activate outside narrowly intended contexts. Over-broad routing increases the chance of inappropriate specialization, unnecessary collection of sensitive family information, or the skill overshadowing safer/general response logic.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The install instruction invokes npx clawhub install parenting-psychology without pinning a specific package version. That makes installation dependent on whatever version is current at execution time, creating a supply-chain risk where a compromised or breaking upstream release could execute unintended code during install.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The 'When to Use' section lists many common, loosely bounded situations without guardrails or negative examples, which broadens invocation scope. In a sensitive domain involving children, that can lead to over-triggering on distress or family-conflict conversations and produce advice in cases that may actually require crisis, legal, or clinical escalation.

Content

No source excerpt is available for this finding.