weekly-sales-briefing

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFEPROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. It retrieves data from an external API and interpolates it into a rendered HTML artifact without sanitization instructions.
  • Ingestion points: SKILL.md (Step 3)
  • Amazon sales data, specifically the product_name field, fetched from the DataDoe API.
  • Boundary markers: None specified. There are no instructions to the agent to treat external strings as untrusted or to ignore instructions embedded within the ingested data.
  • Capability inventory: SKILL.md (Step 8)
  • The agent is instructed to generate a self-contained, interactive HTML/JS card artifact using the external data.
  • Sanitization: Absent. No logic is provided to escape or validate data before it is rendered into the HTML artifact.
  • [DATA_EXFILTRATION]: The skill performs network requests to an external API endpoint (api.datadoe.com) to retrieve production sales and traffic data. This activity is consistent with the skill's documented purpose of generating weekly performance reports.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 02:52 PM
Security Audit — agent-trust-hub — weekly-sales-briefing