frontend-design
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions facilitate a workflow where external, untrusted data (a user-provided design brief) directly influences code generation.\n- Ingestion points: The design brief mentioned in
SKILL.mdserves as the primary input for brainstorming and planning design choices.\n- Boundary markers: The skill does not provide the agent with specific delimiters or instructions to treat the brief's content as data rather than instructions, nor does it warn to ignore potential command-like patterns within the brief.\n- Capability inventory: The skill directs the agent to 'write the code' following the plan derived from the brief, which involves the capability to perform file system operations.\n- Sanitization: There is no mention of validating, filtering, or escaping the content of the design brief before it is processed or used to generate code.
Audit Metadata