ClawHub
Back to skill

Security audit

apple-jobs-research

Security checks across malware telemetry and agentic risk

Overview

The skill’s Apple jobs purpose is clear, but its helper script is broader than that purpose and can act as a generic authenticated Crawlora API client.

Review this skill before installing. It appears intended for public Apple jobs research, but the bundled helper should ideally be restricted to /apple-jobs/search and /apple-jobs/job GET requests. Use a limited Crawlora key, avoid passing sensitive data as parameters or POST bodies, and consider tightening the script before use.

SkillSpector

By NVIDIA
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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
85% confidence
Finding
The skill instructs use of shell commands and external API calls but does not declare permissions or capability boundaries. In an agentic environment, undeclared shell/network capability increases the chance that the skill is executed with broader privileges than reviewers or policy expect, weakening least-privilege controls and auditability.

Description-Behavior Mismatch

Medium
Confidence
91% confidence
Finding
The helper advertises support for unrelated Crawlora endpoints such as Amazon, YouTube, Google search, and Google Trends even though the skill is described as Apple jobs research only. This creates unnecessary capability expansion and makes it easy for downstream prompts or wrappers to repurpose the skill for broader web/data access than users would reasonably expect.

Context-Inappropriate Capability

Medium
Confidence
96% confidence
Finding
The script accepts an arbitrary API path and HTTP method and appends them directly to the Crawlora base URL, effectively exposing a generic authenticated API client. In the context of a narrowly scoped Apple jobs skill, this violates least privilege and can be abused to query unrelated endpoints or perform unintended actions with the provided API key.

External Transmission

Medium
Category
Data Exfiltration
Content
curl -fsS -G "${auth[@]}" "${qs[@]}" "${base}${path}"
else
  [ -n "$body" ] || body="${rest[0]:-{}}"
  curl -fsS -X "$method" "${auth[@]}" \
    -H "Content-Type: application/json" -d "$body" "${base}${path}"
fi
Confidence
84% confidence
Finding
curl -fsS -X "$method" "${auth[@]}" \ -H "Content-Type: application/json" -d

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:21