ads
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes marketing strategy, learnings, and campaign briefs from local files to inform its advertising recommendations.
- Ingestion points: Accesses context from
.agents/marketing-strategy.md,.agents/marketing-learnings.md, and campaign briefs located in.agents/campaigns/. - Boundary markers: The skill relies on the agent's ability to interpret these files as context without explicit delimiters or instructions to ignore embedded commands.
- Capability inventory: The skill is designed to interact with advertising platform tools (Google Ads, Meta Ads, LinkedIn Ads, TikTok Ads) for campaign creation, optimization, and scaling.
- Sanitization: No explicit sanitization or filtering of the ingested marketing data is implemented beyond standard agent safety protocols.
- [SAFE]: The skill provides legitimate marketing documentation, including conversion tracking snippets for well-known services such as Google, Meta, LinkedIn, and TikTok. These are documented neutrally as implementation templates.
Audit Metadata