redesign-existing-projects

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to scan and analyze an existing codebase to identify design weaknesses and apply upgrades. This ingestion of untrusted external content creates a surface for indirect prompt injection, where an attacker could embed malicious instructions within the project's source code files (e.g., in comments or text) to influence the agent's behavior.
  • Ingestion points: The "Scan" step in SKILL.md reads the framework, styling method, and current design patterns from the user's codebase.
  • Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions found within the processed code.
  • Capability inventory: The skill has the capability to modify the codebase through the "Fix" step, which could be exploited if the agent follows instructions hidden in the code it is auditing.
  • Sanitization: No sanitization or validation of the codebase content is performed before it is used to guide the agent's actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 02:56 PM
Security Audit — agent-trust-hub — redesign-existing-projects