ClawHub
Back to skill

Security audit

indeed-research

Security checks across malware telemetry and agentic risk

Overview

The skill is an Indeed job-search helper, but its bundled script can act as a generic authenticated Crawlora API proxy beyond the documented Indeed use case.

Review before installing. The Indeed workflow is clear, but the included helper is not constrained to Indeed and could spend or use the configured Crawlora API key against other Crawlora-backed services if invoked that way. Install only if you are comfortable with that broader authenticated API access, or restrict the script to the three documented Indeed GET endpoints first.

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)

Description-Behavior Mismatch

High
Confidence
95% confidence
Finding
The helper advertises and supports arbitrary Crawlora endpoints such as Amazon, YouTube, Google, and Trends even though the skill is described as Indeed-only. This creates a scope mismatch that can let an agent or user repurpose the embedded API key and skill runtime for unrelated external data access, expanding the attack surface and violating least privilege.

Context-Inappropriate Capability

High
Confidence
97% confidence
Finding
The implementation accepts arbitrary paths, methods, query parameters, and JSON bodies and forwards them directly to Crawlora with the API key attached. In an agent skill, this effectively turns the skill into a generic authenticated proxy to a third-party service rather than a constrained Indeed research tool, enabling misuse, data exfiltration, and unreviewed capability expansion.

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}${path}"
fi
Confidence
88% confidence
Finding
curl -fsS -X "$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