Back to skill

Security audit

business-review-trust-research

Security checks across malware telemetry and agentic risk

Overview

This skill appears to support legitimate business review research, but its bundled helper is broader than the stated purpose and can send authenticated requests to arbitrary Crawlora paths or an overridden API host.

Review this skill before installing if you need strict control over outbound business-intelligence queries or API-key use. Use a scoped, rotatable Crawlora key, avoid sensitive internal project names or confidential vendor lists in queries, and consider restricting the helper to the documented read-only endpoints and fixed Crawlora API host.

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 (9)

Description-Behavior Mismatch

Medium
Confidence
84% confidence
Finding
The TrustMRR startup-listing documentation explicitly advertises that callers can enumerate and scrape an entire directory, which broadens the skill from targeted product/business research into bulk reconnaissance and data harvesting. In this context, that expanded capability increases abuse potential for large-scale collection, profiling, and competitive intelligence beyond the user-facing description.

Description-Behavior Mismatch

Medium
Confidence
96% confidence
Finding
The helper is intentionally generic and allows callers to hit arbitrary Crawlora endpoints, which exceeds the documented business-review/trust-research scope of the skill. In an agent setting, this broad capability can be repurposed to access unrelated data sources or perform unintended actions through the vendor API, undermining least privilege and increasing the blast radius of prompt or tool misuse.

Context-Inappropriate Capability

Medium
Confidence
97% confidence
Finding
The script permits arbitrary HTTP methods and arbitrary JSON bodies to any Crawlora path, effectively exposing a general authenticated API client rather than a narrowly scoped research tool. If an agent or downstream caller is influenced by untrusted input, this enables misuse of the API key for unintended POST or state-changing operations and broadens external data exfiltration opportunities.

Missing User Warnings

Low
Confidence
76% confidence
Finding
The file documents use of an external API key and remote service but provides no warning that user queries and parameters will be transmitted off-platform. That omission can cause unintended disclosure of sensitive search terms, company names, or internal procurement interests to a third party.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The endpoint description says the directory can be enumerated and scraped in full, but includes no caution about collection impact, rate limits, or downstream compliance obligations. That creates a clear path for abusive bulk harvesting and can expose the operator to platform, legal, or reputational risk.

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
92% confidence
Finding
https://api.crawlora.net/

External Transmission

Medium
Category
Data Exfiltration
Content
Endpoints this skill uses, grouped by platform. Call them via `scripts/crawlora.sh` (see SKILL.md).

All paths are relative to the API base `https://api.crawlora.net/api/v1` and require the header `x-api-key: $CRAWLORA_API_KEY`. Path params like `{id}` are substituted into the URL; `GET` params go in the query string; `POST` params go in a JSON body.

**28 endpoints across 4 platform group(s).**
Confidence
88% 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}${path}"
fi
Confidence
91% confidence
Finding
curl -fsS -X "$method" "${auth[@]}" \ -H "Content-Type: application/json" -d

External Transmission

Medium
Category
Data Exfiltration
Content
set -euo pipefail

: "${CRAWLORA_API_KEY:?Set CRAWLORA_API_KEY first — get a free key at https://crawlora.net?utm_source=github&utm_medium=referral&utm_campaign=crawlora-skills}"
base="${CRAWLORA_API_BASE:-https://api.crawlora.net/api/v1}"

method="GET"
body=""
Confidence
84% confidence
Finding
https://api.crawlora.net/

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