ClawHub
Back to skill

Security audit

Indeed Search

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed job-search helper that uses a RolesAPI key and network calls without hidden, persistent, destructive, or unrelated behavior.

Install only if you are comfortable sending job-search keywords and optional locations to RolesAPI and spending RolesAPI credits. Keep ROLESAPI_KEY scoped to this service and revoke it if no longer needed.

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 (5)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The description claims a broader Indeed job search capability with filters for date ranges and remote-only results across country editions. The actual code is narrowly scoped to the remote listings endpoint and only accepts keyword, location, country, and pagination inputs. It does not expose or implement 'today' or 'this week' filtering, and remote-only is not a filter here but the sole behavior. While country selection is partially consistent, the primary functionality is materially narrower than declared.

Content

No source excerpt is available for this finding.

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The code does match the core purpose of searching Indeed job listings by keyword and location via RolesAPI and supports an optional country parameter consistent with multiple country editions. However, the declared description also claims filtering to postings from today, this week, or remote-only. In this code chunk, there are no parameters or logic for date-range filters such as today or this week, and no explicit remote-only filter beyond allowing the user to supply a location string that could be 'remote'. That makes the description materially broader than the implemented behavior in this chunk.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill requires both environment secret access (ROLESAPI_KEY) and outbound network access, but it does not declare an explicit tool scope such as permissions or allowed-tools. That creates an overbroad execution surface where a host agent may grant more capability than users expect, increasing the risk of unintended secret exposure or unauthorized external requests.

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 42)May include surrounding context.

md
**Do NOT use when:**

- A job title or location appears incidentally in context
- The user mentions hiring without asking to search postings
- The user has one specific posting in mind and wants its details. Use [`indeed-full`](https://github.com/nikhonit/indeed-skills/tree/main/skills/indeed-full) instead.

Each results page consumes one credit. The preset scripts can fetch up to 3 pages per call, so cap `--max-pages` for cheap scans.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This Python file makes a POST request to an external API and includes user-provided keyword and location values in the request body. The script has no print/log statement, confirmation, or warning in its docstring explaining that these inputs will be sent over the network.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.