ad-yield-optimization
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and analyze untrusted data from the target codebase, including configuration files and compliance declarations. \n
- Ingestion points: Steps 1.1 and 1.4 involve scanning the codebase for ad stack components and compliance files like ads.txt and sellers.json. \n
- Boundary markers: The instructions lack explicit boundary markers or delimiters to isolate untrusted content from the system prompt. \n
- Capability inventory: The agent has capabilities to read arbitrary files from the codebase and write analysis reports to the filesystem (e.g.,
docs/ad-yield-optimization-analysis.md). \n - Sanitization: There is no evidence of content sanitization or instruction-filtering for the data being analyzed.
Audit Metadata