jmb-tdd

Pass

Audited by Gen Agent Trust Hub on Nov 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists entirely of instructional markdown files and configuration metadata designed to guide an AI agent in TDD practices. No scripts, binaries, or automated command executions are present.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions suggest reading local project files such as CONTEXT.md and Architecture Decision Records (ADRs) to align with project-specific domain language.
  • Ingestion points: Instructions in SKILL.md to read CONTEXT.md and local ADR files from the user's codebase.
  • Boundary markers: Absent; the instructions do not specify delimiters or warnings for the content of these files.
  • Capability inventory: The skill is used to generate source code and test files.
  • Sanitization: No specific sanitization or validation of the ingested file content is mentioned.
  • Assessment: This presents a standard surface for indirect prompt injection where a malicious file in a codebase could attempt to influence the agent's behavior. However, given the skill's purpose (coding and testing), the risk is categorized as low and is inherent to development-oriented tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 19, 2026, 07:02 PM