ClawHub
Back to skill

Security audit

google-jobs-research

Security checks across malware telemetry and agentic risk

Overview

This skill is for Google job searches, but its included helper can use the same API key to call unrelated Crawlora services, so it should be reviewed before installing.

Install only if you are comfortable giving this skill access to a Crawlora API key and you trust agents using it to stay within the Google Jobs endpoints. Prefer a version whose helper enforces an allowlist for /google-jobs/search and /google-jobs/job and removes unrelated examples and arbitrary POST support.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Description-Behavior Mismatch

Medium
Confidence
92% confidence
Finding
The helper is explicitly documented as a generic client for many Crawlora endpoints unrelated to Google Jobs, which exceeds the skill's declared scope. In an agent context, this broad capability can be repurposed to access arbitrary third-party data sources through the same API key, increasing the chance of policy bypass, unintended data access, and misuse beyond user intent.

Context-Inappropriate Capability

Medium
Confidence
96% confidence
Finding
The script accepts an arbitrary API path and method, then concatenates it directly onto the Crawlora base URL, creating a broad proxy to the vendor's entire API. For a narrowly scoped skill, this is dangerous because any caller able to influence arguments can drive requests to unrelated endpoints and send arbitrary JSON payloads with the skill's 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}${path}"
fi
Confidence
90% confidence
Finding
curl -fsS -X "$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:22