product-page-optimizer
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run several local Python scripts (dfs_client.py, schema_gen.py, report_publish.py) with arguments derived from user input or page content. This involves executing commands in a shell environment where inputs like URLs and keywords are directly interpolated.
- [INDIRECT_PROMPT_INJECTION]: The skill fetches and analyzes content from arbitrary product and competitor URLs. This creates a surface for indirect prompt injection where instructions embedded in external web content could influence the agent's logic or the parameters it passes to its scripts.
- Ingestion points: External content fetched from the product URL and competitor pages via dfs_client.py.
- Boundary markers: No specific delimiters or warnings are provided to the agent to treat fetched content as untrusted data.
- Capability inventory: The skill allows the agent to execute Python scripts via the shell, which could be leveraged if the agent is manipulated by injected content.
- Sanitization: The instructions do not specify any validation, filtering, or escaping for data retrieved from the web before it is processed or used in shell commands.
Audit Metadata