ideation

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core workflow of processing untrusted data to generate structured artifacts.
  • Ingestion points: Phase 1 (Intake) in SKILL.md accepts unorganized user input, including voice transcripts and scattered thoughts, which are then used to drive the generation of all subsequent documents.
  • Boundary markers: No explicit delimiters or system instructions are used to separate the user-provided 'brain dump' from the agent's internal logic, increasing the risk that the agent may follow instructions embedded within the user data.
  • Capability inventory: The skill creates and writes to files in the ./docs/ideation/ directory and generates technical specifications (references/spec-template.md) that include shell commands such as pnpm build and pnpm test.
  • Sanitization: The skill lacks validation or sanitization steps to ensure that instructions hidden within the user's input do not manipulate the content of the generated PRDs or implementation specs.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 07:16 AM