periplus-multi-source-enrichment

Pass

Audited by Gen Agent Trust Hub on Nov 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and process data from untrusted external web sources, creating a vulnerability to indirect prompt injection.
  • Ingestion points: The instructions mandate fetching evidence from the web, stating: "Acquire missing evidence or inspect detail pages as necessary" and "use suitable external discovery for missing URLs" (SKILL.md).
  • Boundary markers: There are no instructions defining clear boundaries or delimiters to separate the retrieved external content from the agent's instructions, nor are there warnings to ignore embedded commands within the sourced data.
  • Capability inventory: The skill performs data matching and enrichment, which involves processing untrusted strings and potentially outputting them into a structured dataset or report.
  • Sanitization: The skill lacks any explicit requirement for sanitizing, filtering, or escaping content retrieved from external URLs before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 5, 2026, 04:35 AM