outliner

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill defines a standard workflow for processing user content into outlines. It uses local file storage for organization and does not engage in any suspicious network activity, credential harvesting, or unauthorized command execution.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it processes untrusted user-provided materials.
  • Ingestion points: Material provided by the user is captured and saved as source-1.md in the posts/ directory (SKILL.md, Step 1).
  • Boundary markers: No specific boundary markers (such as XML tags or triple-backticks) are instructed for wrapping the user input to prevent it from being interpreted as instructions by the content-analyzer tool.
  • Capability inventory: The skill is capable of directory creation and file writing within its workspace and can trigger subsequent content analysis and writing tasks.
  • Sanitization: Input materials are not validated or sanitized before being saved or analyzed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 08:23 AM
Security Audit — agent-trust-hub — outliner