Back to skill

Security audit

skill-health-scan

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a benign skill with no AIG findings; the verdict reflects purpose-aligned behavior, with limited cautions about tool scope and persistence and medium overall confidence.

The verdict is benign, but confidence is medium and the scan is partial: two referenced memory-file paths were unresolved. Before installing, consider whether the skill's file-reading capability and memory-state setup fit your needs; the scanners do not establish that the referenced files or behavior are safe.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (2)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: file_read.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

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 66)May include surrounding context.

md
Same core function installed twice — detect by name similarity plus description similarity (≥60% keyword overlap in the trigger phrase). **RED**. Ask before suggesting removal.

### 5. Bloat
Skills that are large (many reference files) AND plausibly never triggered = dead weight loading cost. **YELLOW**, suggest review — never delete without asking.

## Report