Security audit
ponytail-gain
Security checks for vulnerabilities and agentic risk
Overview
This skill displays a fixed benchmark scoreboard and explicitly prohibits edits, mode changes, and persistence.
The scoreboard uses publisher-reported averages, consistent with the [publisher’s README](https://github.com/DietrichGebert/ponytail), rather than measurements of your project. SkillSpector’s incomplete status reflects an unbundled benchmark citation; artifact inspection found no executable or sensitive 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
- 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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
