ClawHub
Back to skill

Security audit

meta-jobs-research

Security checks across malware telemetry and agentic risk

Overview

The skill is for Meta job searches, but it includes a broad Crawlora API helper that can use the user’s key on unrelated endpoints.

Review this before installing. It appears aimed at public Meta job research and does not show destructive behavior, but the included helper is a general Crawlora API wrapper rather than a Meta-only wrapper. Install only if you are comfortable letting the agent use your Crawlora key beyond the documented Meta Jobs endpoints, or restrict the script to /meta-jobs/list, /meta-jobs/search, and /meta-jobs/job 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 Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Context-Inappropriate Capability

Medium
Confidence
96% confidence
Finding
The skill is described as a Meta jobs research tool, but the helper advertises and supports generic Crawlora endpoints such as Amazon, YouTube, Google search, and trends. That creates a capability mismatch: a caller expecting narrowly scoped Meta-careers access can instead drive unrelated third-party data collection through the same authenticated client, expanding data exfiltration and policy-bypass risk.

Description-Behavior Mismatch

High
Confidence
99% confidence
Finding
The script concatenates an arbitrary user-supplied path onto the Crawlora API base and sends authenticated requests to it, so the skill can access any Crawlora endpoint rather than just Meta jobs data. In the context of an agent skill, this is especially dangerous because it defeats least privilege and enables misuse of the API key for unrelated browsing, scraping, or data retrieval under the guise of a benign job-search capability.

External Transmission

Medium
Category
Data Exfiltration
Content
- Get a free Crawlora API key (2,000 credits/mo, no card) at [https://crawlora.net](https://crawlora.net?utm_source=github&utm_medium=referral&utm_campaign=crawlora-skills).
- `export CRAWLORA_API_KEY=sk_your_key_here`
- All requests: `x-api-key: $CRAWLORA_API_KEY` against
  `https://api.crawlora.net/api/v1`. Missing/invalid key → `401`.

## How it works
Confidence
90% confidence
Finding
https://api.crawlora.net/

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}${path}"
fi
Confidence
92% confidence
Finding
curl -fsS -X "$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:23