product-page
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of markdown instructions and evaluation criteria without any executable scripts, binaries, or automated shell commands. It focuses on copywriting quality and product page layout principles.
- [INDIRECT_PROMPT_INJECTION]: The skill establishes an ingestion surface by instructing the agent to read external strategy and learning files for context.
- Ingestion points: The agent is directed to read
.agents/marketing-strategy.md,.agents/marketing-learnings.md, and other related files in the project directory to gather brand context. - Boundary markers: There are no specific delimiters or instructions to treat the content of these external files as untrusted data or to ignore embedded instructions.
- Capability inventory: The skill possesses no capabilities for command execution, network operations, or file system modifications, which significantly limits the risk profile of the ingestion surface.
- Sanitization: No sanitization or validation logic is defined for the external file content.
Audit Metadata