Back to skill

Security audit

Skill Param Confirmer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed preflight confirmation layer that is designed to reduce mistakes before other skills run, not to execute hidden actions itself.

This skill appears appropriate as a parameter-confirmation guardrail. Before installing, understand that it may retain session-level confirmation state and audit logs containing user inputs and selected parameters, so avoid feeding secrets unless the host environment handles those logs appropriately.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Self-Modification

High
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · SKILL.md (reported line 636)May include surrounding context.

md
* query skills
* create skills
* update skills
* delete skills
* sync skills
* publish skills

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 327)May include surrounding context.

md
#### BOOLEAN_CONFIRM

Only yes/no confirmation is needed.

#### MULTI_STAGE_CONFIRM

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 670)May include surrounding context.

md
The following behaviors must not be executed automatically by default:

* automatically overwriting existing content
* automatically sending to third parties
* automatically syncing to external systems
* automatically deleting original resources
* automatically using uncertain inferred values as final values