competitive-ads-extractor

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill is a prompt-only skill consisting of markdown instructions without any executable scripts or binary files.
  • [PROMPT_INJECTION]: Surface for Indirect Prompt Injection detected.
  • Ingestion points: Data is scraped from external sources (Facebook and LinkedIn Ad Libraries) into the agent context.
  • Boundary markers: No markers or 'ignore' instructions are provided to isolate ingested content.
  • Capability inventory: The workflow involves writing data to the file system at '~/competitor-ads/'.
  • Sanitization: No sanitization or validation of the ingested external content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 02:47 PM