ClawHub
Back to skill

Security audit

Indeed Full

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed RolesAPI job-posting lookup toolkit that uses a user-provided API key and makes purpose-aligned API calls.

Install only if you are comfortable using RolesAPI with your ROLESAPI_KEY. Calls may consume API credits and will send search terms, locations, job keys, or pasted Indeed URLs to RolesAPI; use the account/usage script only when you want account status or usage records displayed.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (4)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The declared description presents a job-postings toolkit focused on Indeed search and role-detail retrieval. The supplied code chunk instead performs account introspection and usage-history retrieval against RolesAPI endpoints (/v1/me and /v1/usage). These are materially different resources and capabilities from the declared job-posting functions. This is not a minor supporting detail of the advertised functionality; it represents a different primary purpose.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill advertises scripts that require network access and an API key but does not declare any explicit tool scope or allowed-tools boundary. This weakens least-privilege controls and makes it harder for the host to restrict what the skill may access, increasing the chance of unintended external calls or environment access beyond user expectations.

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 48)May include surrounding context.

md
**Do NOT use when:**

- A job title or company appears incidentally in context
- The user is discussing careers abstractly without asking for data on specific postings
- The user has not signaled they want a job data lookup

When the intent is ambiguous, ask the user to confirm before calling a script. Calls cost credits and can return large records the user may not want.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 164)May include surrounding context.

md
- OpenAPI spec: <https://rolesapi.com/openapi.json>
- REST docs: <https://rolesapi.com/api/roles/> and <https://rolesapi.com/api/listings/>
- Hosted MCP server (zero-install alternative to this skill): <https://api.rolesapi.com/mcp>

## Trademark

Static analysis

No suspicious patterns detected.