ClawHub
Back to skill

Security audit

movie-tv-research

Security checks across malware telemetry and agentic risk

Overview

This movie/TV research skill is not malicious, but it needs review because its API helper can be repurposed beyond the declared movie/TV scope.

Review before installing. Use this only if you are comfortable sending movie/TV queries and identifiers to Crawlora with your API key. Prefer a restricted wrapper or endpoint allowlist, keep the key low-value, monitor Crawlora credit usage, and avoid letting agents use the helper for non-movie/TV Crawlora paths or custom API bases.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The helper accepts an arbitrary API path and is documented with unrelated examples like Amazon, YouTube, Google, and Trends, even though the skill is supposed to be limited to movie/TV research sources. That overbroad capability enables the skill to access unrelated data domains through the same API key, violating least privilege and expanding the blast radius if the skill is misused or prompt-injected.

Context-Inappropriate Capability

Medium
Confidence
96% confidence
Finding
The code directly concatenates a caller-controlled path onto the API base and sends requests with the privileged API key, permitting access to unrelated third-party data domains not justified by the declared skill purpose. In a skill context, this makes prompt abuse more dangerous because an attacker can repurpose a movie/TV research tool into a generic data-fetching proxy.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The documentation instructs the agent to send user-supplied queries and identifiers to a third-party API using an API key, but it provides no user-facing disclosure or consent guidance about off-system transmission. In a research skill, users may supply titles, URLs, IDs, or niche queries they assume are handled locally, so silent external transmission creates a privacy and trust risk.

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.

**96 endpoints across 7 platform group(s).**
Confidence
89% confidence
Finding
https://api.crawlora.net/

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

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:24