Back to skill

Security audit

Oracle-X Development

Security checks for vulnerabilities and agentic risk

Overview

This is a repository-specific development guide for Oracle-X with disclosed, proportionate instructions and no executable payload or hidden behavior.

Install this only if you are working on the Oracle-X codebase. It contains project-specific development rules and quality gates, including guidance around authentication, external data providers, and LLM calls, but I found no hidden execution, persistence, or credential-harvesting behavior.

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
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 (4)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · references/upstream.md (reported line 41)May include surrounding context.

md
is dropped silently** — no error, no warning, just a provider nobody is

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description says to use the skill whenever work 'touches backend/routers, backend/services, backend/prompts, backend/tests or frontend/lib' and whenever someone asks how to add several kinds of components. This is a very broad trigger scope for a large portion of repository work and does not provide clear exclusion conditions or negative examples, increasing the chance of unintended invocation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
98% confidence
Finding

The instruction 'Write code, identifiers and comments in English' imposes a language policy in natural language. Under the policy, forcing a specific language without user opt-in or a clearly documented regional/compliance justification is a violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The markdown states that assertions cover 'the exact Turkish output strings,' which implies a fixed locale requirement in the skill's behavior. Because no user opt-in, configurability, or region-specific justification is provided in this file, this may conflict with language/locale policy expectations.

Content

No source excerpt is available for this finding.