ClawHub
Back to skill

Security audit

entertainment-discovery-research

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed entertainment-research wrapper around the Crawlora API with bounded GET routes and no evidence of hidden persistence, destructive actions, or credential theft.

Install only if you are comfortable sending entertainment search terms, title IDs, and supplied IMDb/TMDB/JustWatch/Rotten Tomatoes/Metacritic URLs to Crawlora using your Crawlora API key. Do not include private identifiers, secrets, or unrelated personal data in queries.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (8)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill invokes shell-based commands (`scripts/crawlora.sh ...`) but does not declare any explicit tool restrictions such as `permissions` or `allowed-tools`. This creates an unnecessary trust gap: an agent/runtime may permit broader shell execution than the skill actually needs, increasing the chance of command misuse, argument injection through downstream composition, or unintended access beyond the documented research workflow.

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.

**70 endpoints across 5 platform group(s).**
Confidence
81% confidence
Finding
This skill is explicitly designed to transmit user-supplied queries and identifiers to an external third-party service at api.crawlora.net using an API key. In a research skill, that means potentially sensitive watch interests, names, URLs, or free-form search terms leave the local environment; the broad multi-platform coverage increases the chance that operators over-share prompts or identifiers without realizing they are sent off-platform.

Description-Behavior Mismatch

Medium
Confidence
98% confidence
Finding
The manifest description scopes the skill to movies and TV titles across entertainment sources, but this endpoint reference exposes `metacritic_game` plus game critic and user review endpoints. That expands the subject matter beyond the claimed title domain and is not implied by the manifest wording.

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.

Description-Behavior Mismatch

Medium
Confidence
97% confidence
Finding
The manifest describes a skill for researching movies and TV titles across IMDb, TMDB, JustWatch, Rotten Tomatoes, and Metacritic. However, the route allowlist explicitly permits `/metacritic/game/...` endpoints, expanding behavior into video game research, which is outside the stated movie/TV scope.

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.

Missing User Warnings

Low
Confidence
82% confidence
Finding
This markdown file documents that all endpoint calls require an `x-api-key` header and use the external Crawlora API, but it does not include any warning that requests send user-supplied query parameters or URLs to a third-party service. For a markdown endpoint reference, that omission reduces transparency about external network use and credential use.

Static analysis

No suspicious patterns detected.