meta-ads-library

Pass

Audited by Gen Agent Trust Hub on May 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill retrieves public advertising data from the Meta Ads Library via the author's Hyper MCP platform and Apify integrations. No unauthorized data access or exfiltration patterns were detected.
  • [SAFE]: All identified URLs and services (app.hyperfx.ai) are legitimate resources belonging to the skill's author or trusted well-known integration providers.
  • [PROMPT_INJECTION]: The skill processes external, untrusted content from Facebook and Instagram ads, which presents an indirect prompt injection surface. However, the risk is negligible as the skill lacks high-privilege capabilities and is limited to data summarization for chat output.
  • Ingestion points: Raw ad creative, bodies, and titles are ingested via the search_facebook_ads and get_facebook_ad_details tools.
  • Boundary markers: None identified in the instruction text to separate scraped ad content from the system prompt.
  • Capability inventory: Limited to text summarization and table formatting within the chat interface; no file system or shell execution access.
  • Sanitization: The skill does not explicitly describe any filtering or sanitization of retrieved ad copy.
Audit Metadata
Risk Level
SAFE
Analyzed
May 2, 2026, 04:20 AM