Security audit

womens-day-support

Security checks for vulnerabilities and agentic risk

Overview

This is a simple women-centered resource skill with no hidden execution, persistence, credential access, or data storage behavior found.

Before installing, users should understand this is specifically a women-centered resource skill and its listed hotlines/resources should be verified for the user's location. The package also has quality issues that may affect reliability, including a typo in the career resource path and a test script that calls a missing handler, but these are not security concerns.

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

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 (4)

Natural-Language Policy Violations

Medium

Confidence: 91% confidence
Finding: The README frames the skill as serving only women and does not describe any opt-in mechanism, inclusive eligibility handling, or a justified demographic restriction. This can lead to discriminatory access patterns or exclusion of users seeking similar support, especially if the assistant enforces the scope based only on gendered wording.

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger list includes broad phrases like "support for women" and "women resources," which can overlap with ordinary user requests and may cause unintended invocation. The manifest also does not provide exclusion conditions or negative examples to clarify when the skill should not activate.

Natural-Language Policy Violations

Medium

Confidence: 82% confidence
Finding: The file repeatedly frames the skill as specifically for 'Women's Day Support' and uses only women-targeted commands such as 'women resources' and 'women help'. This imposes a specific demographic scope in natural-language strings without any visible user choice or documented region/compliance justification, which matches the language/locale-style policy concern for natural-language constraints.

Natural-Language Policy Violations

Medium

Confidence: 82% confidence
Finding: The natural-language description states the skill provides support specifically 'for women,' which imposes a demographic constraint in the skill's framing without any opt-in, inclusivity note, or explanation of scope. Under the policy category, this is a natural-language organizational concern because the skill hard-codes a user-group limitation rather than offering user choice or documenting a justified restriction.

Static analysis

No suspicious patterns detected.