skills/nsantini/gsdl/gsdl-create-prd/Gen Agent Trust Hub

gsdl-create-prd

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes potentially untrusted data from the ".planning/[project-name]/seed.md" file and treats it as the primary source of truth for generating requirements. The instructions lack boundary markers or specific directives to ignore or sanitize embedded instructions within the seed file, creating a surface for indirect prompt injection.
  • Ingestion points: .planning/[project-name]/seed.md (referenced in SKILL.md Step 1).
  • Boundary markers: Absent.
  • Capability inventory: File-read (seed file), File-write (PRD generation).
  • Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 07:22 PM