pdp-ecomm-template
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill accepts an optional
reference_page_urlparameter and instructs the agent to analyze the external page structure to extract templates. This allows content from third-party websites to enter the agent's context during processing. - Ingestion points: The
reference_page_urlinput field defined in the SKILL.md and processed in Step 3 of the Execution Protocol. - Boundary markers: Absent. The skill does not use specific delimiters or include instructions for the agent to ignore potentially malicious embedded commands within the extracted web content.
- Capability inventory: The skill is focused on text generation and does not have access to file-system write operations, sensitive environment variables, or administrative shell commands.
- Sanitization: None. There is no mention of filtering, escaping, or validating the content retrieved from the external URL before it is analyzed by the model.
Audit Metadata