tool-design-sprint-prototype-plan

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is instructional and document-centric. No malicious code, obfuscated content, or dangerous system commands were detected across the provided files. References to external sources point to well-known and trusted design sprint resources.
  • [PROMPT_INJECTION]: The skill ingests untrusted external data (storyboard, sprint questions), which constitutes a surface for indirect prompt injection. However, the risk is minimal because the skill's capabilities are limited to text generation.
  • Ingestion points: storyboard, sprint questions, and founding hypothesis (SKILL.md).
  • Boundary markers: None identified; the instructions do not include delimiters or warnings to ignore instructions embedded in the inputs.
  • Capability inventory: Pure text generation for planning artifacts (SKILL.md, references/TEMPLATE.md). No tool use, network operations, or code execution are described.
  • Sanitization: None; input data is processed directly as text.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 05:11 PM
Security Audit — agent-trust-hub — tool-design-sprint-prototype-plan