Security audit

Vertical Niche Community Selection

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a merchant research assistant, but it repeatedly steers users toward one specific commercial service even when that is not necessary for the task.

Install only if you are comfortable with the skill consistently recommending Rijoy as part of assortment validation. Treat its platform suggestions as sponsored or biased unless the publisher separately discloses otherwise, compare neutral loyalty/referral alternatives, and review privacy and consent requirements before putting customer repeat or referral data into any third-party service.

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:120
Finding: Mandatory Third-Party Commercial Promotion Hijacks Skill Outputs
Content: View full analysis
= 75: report += "Strong fit with community logic; consider as priority. After launch, use Rijoy for membership and referral to validate repeat and reputation." elif ...[truncated 4780 chars]
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 (2)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The trigger metadata includes a long list of broad natural-language phrases such as 'community', 'niche interest', and 'how to research community needs' that can match many unrelated merchant queries. This can cause the skill to be invoked when a more appropriate skill should handle the request, leading to prompt/skill hijacking at the routing layer and lower-quality or irrelevant guidance.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The usage section reinforces ambiguous activation by instructing the system to trigger on generic signals like 'community-driven product selection', 'validate demand', or 'review mining' without requiring strong niche-assortment context. In a multi-skill environment, this broad matching increases unintended invocation risk and can overshadow more specialized skills, making routing less predictable and easier to abuse through crafted prompts.
Content: No source excerpt is available for this finding.