krt-roadmap-cartographer

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a standard documentation utility that extracts project context to create roadmaps. It follows a structured workflow and operates within its stated scope, with no evidence of malicious intent, unauthorized resource access, or persistence mechanisms.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) due to its core function of processing external documents.
  • Ingestion points: The skill scans various repository files, including README.md, STRATEGY.md, and technical specifications as defined in SKILL.md.
  • Boundary markers: No explicit delimiters or boundary markers are defined to isolate external data from the primary instruction set.
  • Capability inventory: The skill writes new files to the docs/ folder and generates suggested prompts for subsequent agent actions.
  • Sanitization: No explicit data sanitization or validation of the content extracted from project documents is performed before it is used to populate output templates.
  • Note: This vulnerability surface is inherent to documentation-analysis skills and does not signify a malicious implementation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 06:56 AM