Lp1
High
- Category
- MCP Least Privilege
- Confidence
- 75% confidence
- Finding
The skill uses 'shell' capability that is not listed in its permissions. This may indicate deceptive intent or missing permission declarations.
- Content
Security audit
Luxury Resale Research
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed read-only research helper that sends marketplace queries to Crawlora, with some broader retail and store-location endpoints users should be aware of.
Install only if you are comfortable using Crawlora as the intermediary for live luxury resale research. Treat searches, listing URLs, seller identifiers, and product interests as data sent to that provider, and avoid using the skill for confidential sourcing strategies unless that is acceptable.
Vulnerability Patterns
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (9)
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 95% confidence
- Finding
This skill is explicitly wired to an external service endpoint, so all searches, listing URLs, seller identifiers, and related parameters are transmitted outside the local trust boundary. In the context of luxury resale research, that can expose commercially sensitive sourcing behavior and user interest patterns to a third party even if the data is not traditionally secret.
- Content
md 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. **162 endpoints across 21 platform group(s).**
Description-Behavior Mismatch
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The manifest describes a skill for researching luxury-fashion and watch resale listings, sold evidence, condition, and seller signals across specialist marketplaces. This endpoint reference includes many direct-brand retail/catalog and physical-store endpoints (for example Balenciaga, Burberry, Gucci, Hermès, Prada, Tiffany, Moncler, GOAT, StockX) that support browsing new inventory, recommendations, and store locations rather than resale-market research.
- Content
Context-Inappropriate Capability
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
Multiple endpoints expose physical store directories and map/geo search capabilities, such as Balenciaga stores, Gucci stores, Hermès stores, Moncler boutiques, Prada stores, and Tiffany stores. Finding retail locations is not an obvious requirement for researching resale listings, sold comparables, condition, or seller signals, and the manifest explicitly says the skill is for sourcing/evidence comparison rather than buying.
- Content
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 60% confidence
- Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
- Content
sh #!/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:
External Transmission
Medium
- Category
- Data Exfiltration
- Confidence
- 60% confidence
- Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
- Content
sh #!/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:
Sudo/Root Execution
Medium
- Category
- Privilege Escalation
- Confidence
- 80% confidence
- Finding
Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
- Content
sh # 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")
Missing User Warnings
Low
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The document instructs callers to send requests, including query and product parameters, to a third-party API using an API key, but it provides no disclosure or warning that user-supplied research inputs will be transmitted off-platform. In a research skill, those inputs may include sensitive interests, target products, seller identifiers, or proprietary sourcing strategies, creating an avoidable privacy and confidentiality risk.
- Content
Context-Inappropriate Capability
Low
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
The skill includes endpoints for static pages, sitemaps, and editorial content, such as Fashionphile/Rebag pages and sitemaps and Tiffany content search. These capabilities enable broader site-content extraction that is not directly tied to researching resale listings, sold evidence, condition, or seller trust signals as stated in the manifest.
- Content