Back to skill

Security audit

Musael Seeded Name Generator API

Security checks for vulnerabilities and agentic risk

Overview

The scanners returned a benign verdict: they found no AIG issues and judged the reported behavior broadly aligned with the skill’s purpose, with one caution and incomplete evidence because a referenced local path was missing.

The verdict is benign, with medium overall confidence. Consider that Skillspector reported one low-risk caution and left the analysis partial because a referenced local path could not be matched to a bundled artifact; the scan does not establish how that reference works.

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
  • 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
Findings (1)

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 21)May include surrounding context.

md
2. Select only a supported kind. Default to fantasy, seed 1, and count 10 when the task gives no preference.
3. Keep seed within 1-999999 and count within 1-20. Preserve the returned kind, seed, names, and source.
4. Check HTTP status. On 429 or 503, honor Retry-After before a later attempt; do not rotate networks or accounts.
5. Present generated names as suggestions. Do not claim that a name is available as a trademark, domain, username, or product identity without checking that separately.
</process>

<privacy_and_scope>