Luxury Resale Research

• Outcome: Pass
• Latest audit: Sep 21, 2026 · 3:08 AM UTC
• Version: 1.0.0

Overview

This skill is a read-only luxury resale research helper that uses a third-party Crawlora API, with some broader public retail/store endpoints that users should treat as ancillary.

Install only if you are comfortable using Crawlora as a third-party service for public luxury marketplace research. Provide a Crawlora API key through the environment, do not paste secrets or private/internal URLs into queries, and treat retail catalog, editorial, and store-locator outputs as background context rather than resale sale evidence.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection

Findings (10)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 70% confidence
• Finding: Without declared permissions the skill's intent is opaque and cannot be validated.

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.

**161 endpoints across 21 platform group(s).**

• Confidence: 78% confidence
• Finding: This skill is explicitly designed to transmit request parameters to an external domain, api.crawlora.net. External transmission is expected for a web-research skill, but it is still security-relevant because URLs, search terms, seller identifiers, and possibly user-provided targets are sent to a third party, which can create privacy, compliance, and data-handling risk if not disclosed and constrained.

Missing User Warnings

Medium

• Confidence: 85% confidence
• Finding: The file instructs users to send requests to an external service using an API key header, but provides no warning about credential handling, least-privilege storage, or the fact that user-supplied query data will be transmitted off-platform. In an agent setting, this can lead to accidental secret leakage, unsafe propagation of sensitive user inputs to third parties, or poor operational handling of the Crawlora credential.

Description-Behavior Mismatch

Medium

• Confidence: 94% confidence
• Finding: The manifest says the skill is for researching luxury-fashion and watch resale listings, sold evidence, condition, and seller signals, and explicitly says it is not for buying or appraisal. This file documents extensive endpoints for first-party retail catalogs and physical store directories across brands such as Balenciaga, Burberry, Gucci, Hermès, Prada, Tiffany, GOAT, and StockX, which materially exceeds resale-listing research and seller-signal collection.

Context-Inappropriate Capability

Medium

• Confidence: 97% confidence
• Finding: The skill's stated purpose is researching resale listings, sold evidence, condition, and seller signals. Endpoints for locating physical stores, exposing phone numbers, coordinates, opening hours, and even in-store appointment links are unrelated to sourcing resale comps and instead support retail shopping or offline visit planning.

Context-Inappropriate Capability

Medium

• Confidence: 97% confidence
• Finding: This file repeatedly documents store-directory access for Gucci, Hermès, Moncler, Prada, and Tiffany. Those capabilities gather retail location data rather than resale listing evidence, sold history, condition data, or seller reputation signals, so they are not justified by the declared luxury-resale-research scope.

External Transmission

Medium

• Category: Data Exfiltration

Content

#!/usr/bin/env bash
# Crawlora REST helper — minimal, dependency-free (curl only).
# Calls https://api.crawlora.net/api/v1 with your Crawlora API key.
# Get a free key (2,000 credits/mo, no card) at https://crawlora.net?utm_source=github&utm_medium=referral&utm_campaign=crawlora-skills.
#
# Usage:

• Confidence: 60% confidence
• Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

External Transmission

Medium

• Category: Data Exfiltration

Content

#!/usr/bin/env bash
# Crawlora REST helper — minimal, dependency-free (curl only).
# Calls https://api.crawlora.net/api/v1 with your Crawlora API key.
# Get a free key (2,000 credits/mo, no card) at https://crawlora.net?utm_source=github&utm_medium=referral&utm_campaign=crawlora-skills.
#
# Usage:

• Confidence: 60% confidence
• Finding: Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Sudo/Root Execution

Medium

• Category: Privilege Escalation

Content

# config supplies the header and is removed automatically on exit.
umask 077
curl_config="$(mktemp "${TMPDIR:-/tmp}/crawlora-curl.XXXXXX")"
chmod 600 "$curl_config"
trap 'rm -f "$curl_config"' EXIT
printf 'header = "x-api-key: %s"\n' "$CRAWLORA_API_KEY" >"$curl_config"
auth=(--config "$curl_config")

• Confidence: 80% confidence
• Finding: Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Context-Inappropriate Capability

Low

• Confidence: 88% confidence
• Finding: The manifest limits the skill to resale listings, sold evidence, condition, and seller signals. Tiffany editorial content search returns style guides and articles rather than listing, pricing, condition, or seller data, making it an unjustified capability for this skill's purpose.

Static analysis

No suspicious patterns detected.