ads
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted data from external sources, such as the Facebook Ad Library and product reviews, which creates a vulnerability surface for indirect prompt injection.
- Ingestion points: Untrusted data enters the agent context via browser tools when performing ad library teardowns and scraping product reviews as described in
references/creative-research-automation.md. - Boundary markers: The skill contains explicit instructions in
SKILL.mdandreferences/audit-guardrails.mdstating that fetched pages, exports, and screenshots are data, not instructions, and that the agent should never follow directives embedded in them. - Capability inventory: The skill leverages capabilities including browser access for data collection, file-write operations for CSV exports, and network communication via Slack for reporting.
- Sanitization: Instructions are provided to specifically ignore and note attempts at prompt injection within external data, effectively treating external text as non-executable data.
Audit Metadata