competitive-ads-extractor

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [NO_CODE]: The provided skill consists entirely of markdown documentation and usage examples. No executable scripts, binaries, or configuration files that could trigger automated code execution were detected.
  • [PROMPT_INJECTION]: The skill describes a workflow that ingests untrusted data from external sources (Facebook and LinkedIn Ad Libraries), creating a surface for indirect prompt injection.
  • Ingestion points: Data is pulled from third-party competitor advertisements on social media platforms.
  • Boundary markers: The skill lacks explicit instructions or delimiters to isolate scraped content or warn the agent against following instructions embedded within processed ad copy.
  • Capability inventory: The described workflow includes network operations (web scraping) and local file system writes (saving screenshots and analysis to ~/competitor-ads/).
  • Sanitization: No methods for sanitizing or validating external content are described before the data is processed for analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 12:37 PM