ad-brief
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from external sources such as scraped ad captions and body text.\n
- Ingestion points: Data is pulled from external databases including Supabase (ad_system.ads) and Airtable records.\n
- Boundary markers: The skill includes an explicit block instructing the agent to treat scraped content as data only and to ignore any instructions found within it.\n
- Capability inventory: The skill utilizes capabilities to read from external databases (Supabase/Airtable), read local configuration files (CLAUDE.md), and write output files to the project directory.\n
- Sanitization: The skill instructs the agent to quote and cease processing if the scraped data attempts to address the AI directly.
Audit Metadata