outline-builder

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The skill utilizes a local Python script at .codex/skills/outline-builder/scripts/run.py to automate tasks. This execution is confined to local skill components.
  • [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection (Category 8) because it processes untrusted data. 1. Ingestion points: Files outline/taxonomy.yml and those in ref/agent-surveys/text/ are ingested into the context. 2. Boundary markers: No explicit markers or ignore-instructions are used during interpolation. 3. Capability inventory: The skill possesses file-write capabilities (outline/outline.yml) and command execution for the local script. 4. Sanitization: No input sanitization or validation logic is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:06 PM