ads-competitor
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted content from external competitor advertisements, which represents a potential surface for indirect prompt injection.
- Ingestion points: Ad headlines, body copy, and creative descriptions retrieved from external platforms (Google Ads Transparency Center, Meta Ad Library, LinkedIn Ad Library, and TikTok Creative Center) as specified in the 'Process' section of SKILL.md.
- Boundary markers: The instructions do not include specific delimiters or warnings to the agent to ignore instructions that might be embedded within the competitor's ad copy.
- Capability inventory: The agent has the capability to read local files (e.g.,
../ads/references/benchmarks.md) and write reports to the local filesystem (COMPETITOR-INTELLIGENCE-REPORT.md,COMPETITIVE-GAPS.md). - Sanitization: There are no explicit steps defined to sanitize or validate the content retrieved from external sources before it is processed and included in the final reports.
Audit Metadata