skills/mdhb2/aix-skillpack/prd/Gen Agent Trust Hub

prd

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill's instructions for document generation and compliance are consistent with its stated purpose of creating PRDs.
  • [COMMAND_EXECUTION]: The skill instructs the agent to use 'mkdir -p .aix' to manage its local workspace. This is a low-risk, standard operation for directory management.
  • [PROMPT_INJECTION]: The skill ingests untrusted user input during the 'Discovery' phase to populate PRD content, creating a surface for indirect prompt injection. Ingestion point: User input during the interrogation phase (SKILL.md). Boundary markers: Absent. Capability inventory: Shell command execution and file writing (SKILL.md). Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 01:22 AM
Security Audit — agent-trust-hub — prd