app-review-mining

• Outcome: Review
• Latest audit: Aug 10, 2026 · 6:37 PM UTC
• Version: 1.0.1

Overview

The skill mostly does what it claims, but its helper script is broader than app review mining and can send arbitrary Crawlora API requests with the user's API key.

Review before installing. Use this only if you are comfortable sending app IDs, search terms, and request parameters to Crawlora with your API key. The helper should be treated as a general Crawlora API client, not a tightly scoped app-review-only tool; avoid sending secrets or proprietary queries unless you have assessed Crawlora's handling of that data.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Description-Behavior Mismatch

Medium

• Confidence: 95% confidence
• Finding: The usage examples explicitly advertise non-app-store endpoints like Amazon, YouTube, Google Search, and Google Trends, which exceeds the skill’s declared purpose of app review mining. This creates a scope mismatch that can let callers use the bundled credentialed helper for unrelated data collection, increasing data exfiltration and policy-bypass risk.

Description-Behavior Mismatch

Medium

• Confidence: 98% confidence
• Finding: The script accepts an arbitrary path and forwards it directly to the Crawlora API with the user’s API key, enabling broad access to the provider’s full API rather than only app-review mining functions. In the context of a narrowly scoped skill, this effectively turns the skill into a generic proxy to an external service and weakens least-privilege boundaries.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The document explicitly directs requests to a third-party API and notes use of an API key, but it does not warn users that their search terms, app identifiers, and other request parameters will be transmitted off-platform. In a skill focused on app research, those inputs can still contain sensitive business intelligence, investigative targets, or proprietary queries, so the omission creates a meaningful data-handling transparency gap.

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.

**23 endpoints across 2 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: 89% confidence
• Finding: curl -fsS -X "$method" "${auth[@]}" \ -H "Content-Type: application/json" -d

VirusTotal

VirusTotal findings are pending for this skill version.

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