x-ads-operator

Pass

Audited by Gen Agent Trust Hub on Oct 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill interacts with external campaign data which can be influenced by external actors, potentially leading to instructions being processed by the agent.
  • Ingestion points: Data retrieved via pull_x_ads_performance, list_campaigns, and get_campaign_observation from the X Ads API.
  • Boundary markers: The skill instructions do not define specific delimiters or instructions for the agent to distinguish between its own logic and data retrieved from the ad platform.
  • Capability inventory: The skill has tools to modify account state, including update_campaign_budget and pause_campaign.
  • Sanitization: No explicit sanitization or filtering of campaign metadata or descriptions is implemented.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 13, 2026, 04:30 PM