Generate-PRD
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's behavior is consistent with its stated purpose of project analysis and PRD generation. No indicators of credential theft, data exfiltration, or malicious persistence were found.\n- [COMMAND_EXECUTION]: The skill uses restricted bash commands (ls, cat, find) to identify the technology stack and conventions of the project being analyzed. These tools are used in a read-only capacity for information gathering.\n- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by reading project files that may contain untrusted data.\n * Ingestion points: Reads project configuration and source files in Phase 1 (SKILL.md).\n * Boundary markers: None explicitly defined to separate project data from instructions.\n * Capability inventory: Limited to writing a JSON file and performing read-only bash operations.\n * Sanitization: No sanitization or validation of the ingested file content is performed before processing.
Audit Metadata