ClawHub
Back to skill

Security audit

tiktok-research

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed TikTok research helper that sends bounded public-data queries to Crawlora using the user's API key.

Install only if you are comfortable sending TikTok research queries and filters to Crawlora with your Crawlora API key. Treat results as public, sampled, time-dependent data, and use the narrower ad-research skill for dedicated competitor-ad comparisons if you want tighter routing.

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 (12)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The manifest describes the skill as general public TikTok research, but the body also includes /tiktok/top-ads/* intelligence workflows that belong to a narrower ad-research domain. This mismatch can mislead reviewers and downstream agents about what the skill is allowed to do, causing it to be selected in contexts where ad intelligence access, comparisons, or compliance review would otherwise require separate scrutiny.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding

The skill documents shell-based execution (scripts/crawlora.sh ...) but does not declare any explicit tool scope or permissions boundary. That creates an authorization and review gap: an agent or platform may allow shell execution more broadly than intended, increasing the chance of unintended command use, data access, or unsafe composition with user-controlled inputs.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The documented scope expands from public TikTok research into Top Ads intelligence within the skill body, which is a scope-definition inconsistency. While not an exploit by itself, it weakens governance by blurring boundaries between general research and ad-focused analysis, making overbroad use more likely.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest describes the skill as researching public TikTok profiles, videos, comments, hashtags, search results, trending feeds, and Creative Center signals, and explicitly says to use a different skill for ad-only comparisons. This endpoint set nevertheless includes a substantial Top Ads surface for ad listing, detail, recommendations, spotlight, and analysis, which extends beyond the described scope of this skill.

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 17)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 · reference/endpoints.md (reported line 7)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:

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest says this skill should be used for public TikTok profiles, videos, comments, hashtags, search results, trending feeds, and Creative Center signals, and explicitly says to use a separate tiktok-ad-research skill for ad-only comparisons. However, the allowed route catalog includes multiple /tiktok/top-ads/* endpoints, which implement ad-research capability inside this skill.

Content

No source excerpt is available for this finding.

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 126)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")

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file explains that the skill calls remote endpoints via scripts/crawlora.sh and requires the x-api-key: $CRAWLORA_API_KEY header, but it does not include any warning about sending queries/data to an external service or using stored credentials. For a skill reference that enables network operations, a brief disclosure would help users understand privacy and credential implications before use.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The comment states the helper is limited to its documented Crawlora route set and should keep unrelated API routes out. Yet the route allowlist later includes /tiktok/top-ads/* endpoints, which conflicts with the manifest guidance to use a different skill for ad-only comparisons, making the documentation misleading about actual scope boundaries.

Content

No source excerpt is available for this finding.