design-brand-guardian
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external information such as business requirements, audience research, and competitive landscape data, which constitutes a potential surface for indirect prompt injection.
- Ingestion points: User-provided business requirements, market research, and target audience data enter the agent context during the 'Brand Discovery and Strategy' phase.
- Boundary markers: The skill does not explicitly instruct the agent to use delimiters or ignore instructions embedded within the ingested data.
- Capability inventory: The skill uses a shell script (
scripts/run.sh) to invoke a Python runner script (run-skill.py), which is a standard execution pattern. - Sanitization: There is no evidence of input validation or sanitization for the data processed by the agent.
Audit Metadata