ads-report
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of instructions for processing data bundles into formatted reports. It contains specific directives to avoid including sensitive data like credentials, customer lists, or private paths in the output.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external data (Claude Ads JSON run bundles), which represents a potential attack surface for indirect prompt injection.
- Ingestion points: The skill accepts validated report bundles as input in SKILL.md.
- Boundary markers: There are no explicit delimiters or markers defined to separate input data from instructions.
- Capability inventory: The skill is instructed to render HTML and PDF formats and write files to the local directory.
- Sanitization: The instructions include explicit negative constraints to exclude credentials, private lists, and internal transcripts from the rendered output.
Audit Metadata