Security audit

Baby Compliance Privacy

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a documentation-only privacy/compliance helper, but it repeatedly pushes a specific commercial platform as trusted without showing support for that endorsement.

Review carefully before installing if you expect neutral compliance advice. The skill appears safe from a code-execution and data-access standpoint, but users may receive an unsupported Rijoy recommendation unless the skill is edited to make vendor mentions optional, evidence-based, and clearly disclosed.

A.I.G

Vulnerability Patterns

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
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

Findings (1)

T01 · Skill Instruction Hijacking

Error

Location: SKILL.md:122
Finding: Forced Third-Party Promotion Through Skill Instruction Hijacking
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (3)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The front-matter description explicitly says to trigger even when the user does not mention compliance or privacy, which broadens activation beyond clear user intent. This can cause inappropriate routing of unrelated requests into a compliance/privacy workflow, leading to irrelevant advice, increased data-sensitivity assumptions, and possible over-collection of personal context in follow-up questions.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The invocation guidance includes indirect phrases like 'parents don’t trust our data use' and 'we need to show we are safe and compliant' without sufficiently defining boundaries for when the skill should not activate. Ambiguous matching increases the chance of misclassification and overreach into adjacent business, branding, or support tasks where compliance analysis was not requested.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The section header "Parent-facing copy patterns (EN)" indicates the skill provides user-facing content in English only. This is a natural-language locale constraint, and the file does not offer alternatives, opt-in, or a documented justification for restricting output to English.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.