ui-ux-design
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates on untrusted project data during its "Audit mode," where the agent is instructed to read the project's own agent documentation, enumerate routes, and analyze component code. It also has the capability to write approved findings into repository files like
SESSION_PROGRESS.mdorROADMAP.md. This interaction with external, potentially attacker-controlled data could allow malicious instructions hidden in the codebase or documentation to influence the agent's behavior. - Ingestion points:
SKILL.md(Reading project's agent doc, routes, and rendered components inAudit mode). - Boundary markers: The instructions do not specify the use of delimiters or specific warnings to ignore embedded instructions within the ingested project files.
- Capability inventory: The skill utilizes file system read access to analyze the project and file system write access to update progress and roadmap files (
SKILL.md,references/PROCESS.md). - Sanitization: There are no explicit instructions for sanitizing or escaping the content retrieved from the project files before the agent processes or acts upon it.
Audit Metadata