Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 1. Delete this `SKILL.md`.
Security audit
beckmann-x-self-improving-proactive
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed orchestration skill that uses persistent self-improving memory and pinned dependencies, with no artifact evidence of hidden execution, exfiltration, or deception.
Install only if you are comfortable with a skill that maintains persistent self-improving memory under ~/self-improving and depends on the two pinned skills. Verify the dependency hashes on install, and use clean uninstall if you want #beckmann memory entries removed later.
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)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md 1. Delete this `SKILL.md`.
Static analysis
No suspicious patterns detected.