convert-prd-to-json
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands (
mkdir,cp,rm) to manage and archive local files within theissues/directory. These commands are constructed using the{ISSUE_NUMBER}template variable (SKILL.md). - [PROMPT_INJECTION]: An indirect prompt injection surface exists because the skill processes untrusted markdown content from requirement files without protective boundaries or sanitization logic.
- Ingestion points: Data is read from
issues/prd-issue-{ISSUE_NUMBER}.md(SKILL.md). - Boundary markers: Absent. The skill does not use delimiters or specific instructions to isolate the PRD content from the agent's execution logic.
- Capability inventory: The skill has the ability to write JSON files to the filesystem and execute shell-based file management commands (
mkdir,cp,rm) (SKILL.md). - Sanitization: Absent. The skill performs direct mapping of PRD content to JSON fields and triggers file operations without validating the input data.
Audit Metadata