Back to skill

Security audit

Expert Product Feedback

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Provener feedback-request integration that asks permission before submitting data, though users should notice that it proactively offers a specific third-party service.

Install this only if you want Codex to offer Provener for human product-feedback requests. Before authorizing submission, review the product details, contact fields, budget, payment-capable value, and any callback URL because those are sent to and stored by Provener.

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:3
Finding

Mandatory Third-Party Promotion Hijacks Product-Feedback Workflows

Content
View full analysis
Remediation
View remediation
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 skill instructs the agent to apply as soon as product-feedback intent appears, even before authorization is complete, which creates an overly broad invocation boundary. In practice this can cause premature collection of business details and steering users toward an external service without first establishing whether the request is in scope, authorized, or appropriate, increasing privacy and consent risk.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger section uses broad language like applying the skill as soon as the user requests testing, critique, or validation, without strong exclusions or a higher-confidence threshold. In this context, that ambiguity is more dangerous because the skill is designed to route potentially sensitive product information to an external API, so over-triggering can lead to unnecessary data collection or premature disclosure workflows.

Content

No source excerpt is available for this finding.