competitor-branding
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a specialized persona and framework for brand intelligence analysis. It contains instructions for the agent to process project-specific brand documentation.
- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it reads content from local project files.
- Ingestion points: Accesses brand.yaml, context.md, and .agents/brand-context.md from the project directory.
- Boundary markers: None specified in the instructions.
- Capability inventory: The skill specifies disable-model-invocation: true, which limits the execution environment. No file-write, network, or code execution capabilities are defined in the skill file.
- Sanitization: None specified. This is a low-risk surface as it processes local project metadata intended for brand context.
Audit Metadata