Security audit

ponytail-review

Security checks for vulnerabilities and agentic risk

Overview

This skill reviews code and reports findings without requesting code changes, privileged access, or persistent activity.

Specify the repository or change to review. Expect related code, tests, and documentation to be read and a report in simple English; proposed fixes are not applied.

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

Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
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 (1)

The output instructions require English without offering a user language choice.

Medium

Category: Output Handling
Confidence: 90% confidence
Finding: “Very simple English” specifies a natural language for the review, rather than only requesting clear wording. The skill provides no language opt-in or justification for restricting output to English.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.