competitive-ads-extractor
Pass
Audited by Gen Agent Trust Hub on Mar 6, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists exclusively of markdown documentation (SKILL.md). No executable code, scripts, binaries, or dependency files were provided for analysis.
- [PROMPT_INJECTION]: The skill describes a workflow that ingests and processes untrusted data from external sources, which constitutes an indirect prompt injection risk. * Ingestion points: Scraped ad copy, headlines, and creative metadata from the Facebook Ad Library and LinkedIn. * Boundary markers: The documentation does not specify any delimiters or instructions to ignore embedded commands in the scraped data. * Capability inventory: The described workflow involves network read operations (scraping) and file system write operations (saving screenshots and reports to ~/competitor-ads/). * Sanitization: No sanitization, validation, or escaping of the ingested ad content is mentioned or implemented.
Audit Metadata