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.json and campaign audit data from ADS-AUDIT-REPORT.md or *-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-strategist and copy-writer agents.
  • 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
Risk Level
SAFE
Analyzed
Apr 5, 2026, 06:41 PM
Security Audit — agent-trust-hub — ads-create