plan-design-review

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: This skill is composed entirely of markdown documentation and does not contain any scripts or executable files.
  • [EXTERNAL_DOWNLOADS]: The skill references an external repository at github.com/garrytan/gstack for the full workflow assets. The documentation suggests manual inspection and installation by the user.
  • [INDIRECT_PROMPT_INJECTION]: The skill's purpose is to analyze user-provided design work, which is a common vector for instructions hidden in data. However, the skill itself provides no automated capabilities that could be exploited.
  • Ingestion points: Reviewing UI work and code provided in the agent context (SKILL.md).
  • Boundary markers: No specific delimiters or warnings for embedded instructions are provided.
  • Capability inventory: None (documentation only).
  • Sanitization: No content validation or sanitization is implemented in the skill description.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 06:12 AM
Security Audit — agent-trust-hub — plan-design-review