skills/miketromba/skills/loops/Gen Agent Trust Hub

loops

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates documentation research by fetching and processing external content from loops.so, which creates a surface for indirect prompt injection.
  • Ingestion points: External documentation index at https://loops.so/docs/llms.txt and individual markdown documentation pages.
  • Boundary markers: Absent. The skill provides no instructions to separate documentation content from instructions or to disregard potentially malicious commands embedded in the documents.
  • Capability inventory: The skill uses a sub-agent for research, and the resulting information is used to perform development tasks such as API integration or email configuration.
  • Sanitization: There is no validation or sanitization of the content fetched from the remote source.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 08:00 PM