utility-pm-workflow-builder

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill ingests user input to generate workflow instructions, creating an indirect prompt injection surface.
  • Ingestion points: User-provided workflow ideas and skill sequences (SKILL.md).
  • Boundary markers: Absent; user input is directly incorporated into the draft markdown templates.
  • Capability inventory: Reading files in _workflows/ and writing to _staging/workflows/ (SKILL.md).
  • Sanitization: Absent; the skill relies on the mandatory human review and promotion step described in the output format instructions.
  • [SAFE]: File access is restricted to the local project repository for the purpose of checking workflow overlaps and writing drafts to a staging area. No access to sensitive user data or system configuration was detected.
  • [SAFE]: The skill does not perform any automated command execution. While it references various validation scripts in its checklist, these are explicitly defined as manual tasks for the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 09:09 PM
Security Audit — agent-trust-hub — utility-pm-workflow-builder