prd-writing
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, executable code, or suspicious behaviors were identified in the skill.- [PROMPT_INJECTION]: The instructions are standard guidelines for PRD writing and do not attempt to bypass AI safety constraints or extract system prompts.- [DATA_EXFILTRATION]: The skill does not perform any network operations or access sensitive local files.- [REMOTE_CODE_EXECUTION]: No external dependencies, script downloads, or dynamic code execution patterns are present.- [COMMAND_EXECUTION]: The skill does not invoke any system commands or subprocesses.- [INDIRECT_PROMPT_INJECTION]: The skill has a minimal attack surface for indirect injection. * Ingestion points: Processes user-provided feature descriptions via the
/prd-writing <feature>command inSKILL.md. * Boundary markers: Absent; the skill does not define specific delimiters for user-provided feature content. * Capability inventory: None; the skill is limited to generating text and does not have access to file systems, networks, or shell execution. * Sanitization: Absent; no sanitization of user input is specified.
Audit Metadata