outline

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of reading external content.\n
  • Ingestion points: Untrusted document content is ingested via the search, read, and list-documents operations in scripts/outline.py.\n
  • Boundary markers: The skill does not implement specific delimiters or instructions to the agent to ignore potentially malicious instructions embedded within wiki content.\n
  • Capability inventory: The skill includes network access via the httpx library and the ability to write document content to local file paths using the export command with the --output flag.\n
  • Sanitization: There is no evidence of content sanitization or validation for the text returned from the Outline API.\n- [EXTERNAL_DOWNLOADS]: The skill performs legitimate network operations to the Outline API (defaulting to https://app.getoutline.com/api) to retrieve and manage wiki documents.\n- [CREDENTIALS_UNSAFE]: The skill requires an OUTLINE_API_KEY for authentication. It correctly instructs users to manage this secret via environment variables or a local .env file, which is a standard and recommended practice.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 12:53 PM
Security Audit — agent-trust-hub — outline