documentation

Pass

Audited by Gen Agent Trust Hub on Nov 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and modify existing documentation files which may contain untrusted content. 1. Ingestion points: Reads AGENTS.md, numbered chapters (01–09), and companion materials such as guide/README.md, guide/READING.md, and guide/FAQ.md (SKILL.md). 2. Boundary markers: The instructions do not specify any boundary markers or delimiters to isolate content being read from the repository. 3. Capability inventory: The skill has the capability to read from and write to various markdown, JSON, and metadata files within the repository structure (SKILL.md). 4. Sanitization: No explicit sanitization or validation steps are mentioned for the content being processed or cross-linked.
  • [SAFE]: Refers to documentation and changelogs on the official Adobe GitHub repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 5, 2026, 01:15 AM