ads-create
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by ingesting and processing untrusted data from local files and user inputs which are then passed to sub-agents.
- Ingestion points: The skill reads brand information from
brand-profile.jsonand campaign audit data fromADS-AUDIT-REPORT.mdor*-audit-results.md. It also accepts user-provided website URLs and brand descriptions. - Boundary markers: Absent. The instructions do not define delimiters or specific "ignore" instructions when interpolating the ingested data into the tasks for the
creative-strategistandcopy-writeragents. - Capability inventory: The skill has the ability to write to the local file system (
campaign-brief.md) and orchestrate other AI agents via a task tool. - Sanitization: Absent. There is no evidence of filtering, validation, or escaping of the data retrieved from external sources before it is processed by the AI pipeline.
Audit Metadata