skills/tobihagemann/turbo/create-spec/Gen Agent Trust Hub

create-spec

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were detected in the skill's instructions or logic. The skill follows its stated purpose of guiding a project discussion and writing a specification to a local file.
  • [PROMPT_INJECTION]: The skill processes user-provided project ideas and discussion content to generate a specification file (.turbo/spec.md), creating a surface for indirect prompt injection.
  • Ingestion points: User input during the 'Capture the Vision' and 'Deep-Dive Discussion' phases (SKILL.md).
  • Boundary markers: Absent; the agent is not explicitly instructed to treat user input as untrusted data or use delimiters.
  • Capability inventory: File writing to .turbo/spec.md (SKILL.md). No command execution or network operations are present.
  • Sanitization: Absent; user input is synthesized directly into the final document.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 10:37 AM