skills/vm0-ai/vm0-skills/tiktok-ads/Gen Agent Trust Hub

tiktok-ads

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill incorporates user-provided identifiers (e.g., advertiser-id, campaign-id) into shell command templates and temporary JSON files, creating an indirect prompt injection surface.
  • Ingestion points: Placeholders like {advertiser-id} and {campaign-id} in SKILL.md are intended to be filled with user input.
  • Boundary markers: There are no specific delimiters or instructions for the agent to treat this content as untrusted data.
  • Capability inventory: The skill utilizes curl for network requests and cat for file creation in the /tmp/ directory.
  • Sanitization: No sanitization or validation steps are defined for the input placeholders.
  • [COMMAND_EXECUTION]: The skill utilizes shell commands (curl, jq, cat) to communicate with the TikTok Ads API and manage local data. This is expected behavior for a CLI-integrated skill.
  • [EXTERNAL_DOWNLOADS]: The skill makes network requests to https://business-api.tiktok.com, which is the official endpoint for the TikTok Business API. These connections are necessary for campaign management.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 01:53 AM
Security Audit — agent-trust-hub — tiktok-ads