tdd-orchestrator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The skill uses a simple cat command to read local memory files in the .specweave directory. This is used for context retrieval and does not involve executing untrusted input.
  • [PROMPT_INJECTION] (SAFE): No instruction overrides or bypass attempts were found. The skill remains within its documented scope of TDD orchestration.
  • [DATA_EXFILTRATION] (SAFE): No network requests or access to sensitive system credentials (e.g., .ssh, .aws) were identified.
  • [INDIRECT_PROMPT_INJECTION] (SAFE): While the skill ingests data from .specweave/skill-memories/tdd-orchestrator.md, this is an internal state file used for historical context. There is no evidence of this being used to process untrusted external data without sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:01 PM