skills/kriscard/skills/ideation/Gen Agent Trust Hub

ideation

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes unstructured user data and interpolates it into markdown templates that are written to the local file system.
  • Ingestion points: Phase 1 (Intake) in SKILL.md accepts arbitrary user-provided thoughts, transcripts, and notes.
  • Boundary markers: The skill does not employ delimiters or specific instructions to prevent the agent from following malicious commands that might be embedded in the user's project descriptions.
  • Capability inventory: The skill possesses file-writing capabilities used to generate contract.md, prd-phase-N.md, and spec-phase-N.md artifacts.
  • Sanitization: No validation or sanitization of the intake data is performed before it is used to populate implementation documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 06:36 PM
Security Audit — agent-trust-hub — ideation