bmad-product-planning

Warn

Audited by Gen Agent Trust Hub on Feb 21, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • Unverifiable Dependencies (MEDIUM): The process instructions in SKILL.md explicitly direct the agent to run scripts/generate_prd.py. Since the script is not included in the analyzed files, its security posture cannot be verified, posing a risk of arbitrary command execution or unauthorized file access.
  • Indirect Prompt Injection (LOW): The skill is designed to process untrusted external data, making it vulnerable to indirect prompt injection. 1. Ingestion points: discovery_artifacts (briefs, research memos, or notes). 2. Boundary markers: Absent; there are no instructions for the agent to use delimiters or ignore instructions embedded in the artifacts. 3. Capability inventory: Read, Write, and Grep tools, plus the execution of scripts/generate_prd.py. 4. Sanitization: Absent; the skill does not specify any validation or sanitization of the input data before processing or script execution.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 21, 2026, 05:42 PM