periplus-data-extraction

Pass

Audited by Gen Agent Trust Hub on Nov 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to extract data from external sources, which may contain adversarial content designed to influence agent behavior.
  • Ingestion points: Processes content from arbitrary web pages, product lists, directories, and captured documents (SKILL.md).
  • Boundary markers: Absent. The instructions do not define delimiters or provide warnings for the agent to ignore instructions found within the source material.
  • Capability inventory: The skill utilizes the Periplus toolset for web crawling, following detail-page links, expanding paging URLs, and processing structured data (JSON/SQL).
  • Sanitization: Absent. There are no instructions for validating, escaping, or filtering the extracted strings before they are returned to the agent context.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 5, 2026, 04:35 AM