ClawHub
Back to skill

Security audit

real-estate-autos-research

Security checks for vulnerabilities and agentic risk

Overview

This skill is a bounded Crawlora API helper for real-estate and car research, with one transparency issue around undeclared Rightmove endpoints but no evidence of malicious behavior.

Before installing, confirm you are comfortable sending real-estate and vehicle search inputs, including addresses, ZIP codes, listing URLs, and property or vehicle IDs, to Crawlora and potentially upstream listing sources. The publisher should update the description to clearly mention Rightmove or remove those routes if they are unintended.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (10)

Tp4

High
Category
MCP Tool Poisoning
Confidence
94% confidence
Finding

The code largely matches the stated purpose of querying Crawlora for real-estate and auto data via specific provider routes and returning JSON. It is constrained to GET requests and an explicit route catalog, which is consistent with a search/lookup helper. However, the declared description says the skill covers Zillow and Redfin for homes plus CarMax, Autotrader, and Cars.com for vehicles, while the actual code additionally exposes Rightmove routes (including agent, property, commercial, new homes, student, and autocomplete endpoints). That is an undeclared capability and access to an inconsistent resource set, so this should be flagged as a mismatch.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

The skill instructs use of a shell helper (scripts/crawlora.sh) but does not declare any tool scope or allowed-tools restrictions. That creates unnecessary execution latitude for an agent runtime and weakens least-privilege guarantees, increasing the chance of unintended shell use or abuse if the skill is invoked in a broader environment.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The documentation explicitly instructs callers to send requests to an external API using an API key, but it does not provide any user-facing disclosure or limitations around what query data may be transmitted. In a research skill that may accept addresses, ZIP codes, URLs, or listing identifiers from users, this can cause silent transmission of potentially sensitive user-supplied data to a third party.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
87% confidence
Finding

This file confirms outbound network access to a third-party service and use of an authentication secret for those calls. External transmission is expected for this skill's purpose, but it still represents a real security/privacy concern because user-supplied search terms, property URLs, IDs, and location data can be sent off-platform, and any misuse or compromise of the API key broadens that exposure.

Content

Scanner excerpt · reference/endpoints.md (reported line 7)May include surrounding context.

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.

**28 endpoints across 6 platform group(s).**

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill metadata says it researches homes and used cars via Crawlora using Zillow, Redfin, CarMax, Autotrader, and Cars.com, but this endpoint reference additionally documents Rightmove capabilities. That mismatch expands the skill's actual reachable behavior beyond what users and reviewers would expect, creating a scope-transparency problem that can lead to unintended external queries and policy bypass through undocumented functionality.

Content

No source excerpt is available for this finding.

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

Scanner excerpt · SKILL.md (reported line 23)May include surrounding context.

md
#!/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

Scanner excerpt · scripts/crawlora.sh (reported line 3)May include surrounding context.

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

Scanner excerpt · scripts/crawlora.sh (reported line 20)May include surrounding context.

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

Scanner excerpt · scripts/crawlora.sh (reported line 109)May include surrounding context.

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")

Vague Triggers

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

This markdown file describes what the skill 'uses' and how to call it, but it does not specify any explicit trigger phrases, scope limits, or exclusion conditions for when the skill should activate. In a skill ecosystem where markdown content may inform routing, this broad description increases ambiguity about when the skill is appropriate versus out of scope.

Content

No source excerpt is available for this finding.