Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - `SKILL.md` — This file
Security audit
Self Audit
Security checks for vulnerabilities and agentic risk
Overview
This skill is a small self-auditing concept that asks users to log tool calls for later analysis, with no bundled executable or hidden behavior found.
Before installing, be aware that a working version of this skill would record tool names, inputs, reasons, and context in local audit logs. Avoid logging secrets, credentials, private customer data, or sensitive business details unless you have a retention and deletion plan. Also note that this package appears to be missing the advertised self-audit CLI script.
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
Findings (2)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The skill explicitly says it logs every tool invocation with context and stores audit logs, but it does not warn users that this data may be written to persistent storage. Tool inputs and reasons can contain sensitive prompts, identifiers, secrets, or business context, so undisclosed retention creates a privacy and data-handling risk. The self-audit context makes this more dangerous because comprehensive logging is the core feature, increasing both collection scope and likelihood of sensitive data capture.
- Content
Static analysis
No suspicious patterns detected.