create-prd
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The instructions are task-oriented and do not contain any patterns intended to bypass safety filters, extract system prompts, or override agent constraints.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from web searches and user-provided files to generate documentation. While it lacks explicit delimiters for this external content, this behavior is a core requirement for its primary purpose of market research and product documentation.
- Ingestion points: External URLs via web search and user-provided files (SKILL.md).
- Boundary markers: None explicitly defined in the instructions.
- Capability inventory: File-write capability to save markdown documents (PRD-[product-name].md).
- Sanitization: None specified for external data.
- [EXTERNAL_DOWNLOADS]: The skill includes links to educational resources on product management from a well-known industry blog (productcompass.pm). These are informational references and do not involve downloading executable code or scripts.
- [COMMAND_EXECUTION]: No shell commands, subprocess spawning, or system-level operations were detected. The file-saving instruction is a standard document management task.
- [DATA_EXFILTRATION]: There is no evidence of hardcoded credentials, access to sensitive local paths, or unauthorized data transmission to external servers.
Audit Metadata