product-spec

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its primary data ingestion points.
  • Ingestion points: The skill ingests untrusted data from user-provided briefs and external websites via the WebFetch operation in SKILL.md.
  • Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the fetched or provided content.
  • Capability inventory: The agent has the capability to write files to the data/products/ directory and modify data/products/index.csv.
  • Sanitization: The instructions do not define any sanitization, validation, or escaping logic for the external content before it is processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill uses a WebFetch tool to download and parse content from user-provided URLs to extract product information such as headlines, pricing, and FAQs. While a core feature, this operation exposes the agent to malicious content hosted on external domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 07:15 AM
Security Audit — agent-trust-hub — product-spec