competitive-ads-extractor

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (HIGH): The skill is designed to ingest and analyze untrusted external content (ad copy and messaging) from public platforms.
  • Ingestion points: Web scraping of Facebook Ad Library and LinkedIn ads as described in the 'What This Skill Does' section.
  • Boundary markers: None detected. The skill instructions do not specify any delimiters or instructions to the agent to ignore embedded commands within the scraped data.
  • Capability inventory: The skill performs file system write operations (saving to ~/competitor-ads/) and potentially network operations for scraping.
  • Sanitization: No sanitization or validation of the ingested text is mentioned. An attacker could place malicious instructions in an ad's copy to hijack the agent during the 'Analyzing messaging' phase.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 10:23 AM