resale-secondhand-research

• Outcome: Review
• Latest audit: Aug 10, 2026 · 6:48 PM UTC
• Version: 1.0.1

Overview

The skill mostly fits resale marketplace research, but its helper can call arbitrary Crawlora API paths and includes unrelated examples, so users should review its scope before installing.

Install only if you are comfortable sending marketplace search terms, seller/shop names, listing IDs, and filters to Crawlora using your API key. Use the helper only for the documented resale marketplace endpoints, and avoid sending personal, confidential, or secret data in queries or JSON bodies.

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 (6)

Description-Behavior Mismatch

Medium

• Confidence: 95% confidence
• Finding: The helper exposes arbitrary Crawlora API paths and methods, while the skill is described as only researching secondhand and resale marketplaces. That scope mismatch enables the agent or a prompt-influenced caller to use unrelated endpoints and transmit data beyond the user’s expected purpose, weakening least-privilege boundaries.

Intent-Code Divergence

Medium

• Confidence: 90% confidence
• Finding: The file is documented as a generic REST helper and includes examples for unrelated services such as Amazon, YouTube, Google search, and trends. This contradicts the declared marketplace-specific intent and increases the chance the skill will be repurposed for broader external browsing or data exfiltration than users or reviewers expect.

Missing User Warnings

Low

• Confidence: 88% confidence
• Finding: The file explicitly instructs callers to send requests to an external API using an API key, but it does not include any user-facing warning that user queries, seller names, listing IDs, or other inputs may be transmitted off-platform to Crawlora. In a research skill, this creates a real transparency and privacy risk because users may assume the assistant is using only internal capabilities rather than forwarding their request data to a third party.

Missing User Warnings

Medium

• Confidence: 87% confidence
• Finding: The script sends user-supplied query parameters or JSON bodies directly to an external third-party API without any runtime notice, consent gate, or data classification check. In an agent setting, that can cause sensitive user data, prompts, or identifiers to be transmitted off-platform without clear user awareness.

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.

**39 endpoints across 7 platform group(s).**

• Confidence: 95% 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: 90% 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:23