generate-prd
Pass
Audited by Gen Agent Trust Hub on Mar 19, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection because it processes untrusted data from GitHub issues (via the
analyze-issuestep) to generate PRD content. - Ingestion points: Reads analysis output derived from external GitHub issues (SKILL.md).
- Boundary markers: Absent; the skill does not use delimiters to separate instructions from the issue data being processed.
- Capability inventory: Includes directory creation (
mkdir -p) and file writing to local paths (SKILL.md). - Sanitization: No validation or sanitization of the input data or the
{ISSUE_NUMBER}variable is specified, which could theoretically allow for path traversal if the issue identifier contains malicious characters. - [COMMAND_EXECUTION]: The skill performs shell commands to manage the local file system.
- Evidence: Uses
mkdir -p issuesto ensure the target directory exists before file creation (SKILL.md).
Audit Metadata