skills/c0nant/skills/tdd/Gen Agent Trust Hub

tdd

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill is a documentation-only extension providing rules and principles for red-green-refactor workflows. It contains no commands, scripts, or automated tool invocations.
  • [INDIRECT_PROMPT_INJECTION]: The instructions direct the agent to read CONTEXT.md to align with project-specific domain language. While this is an ingestion point for untrusted data, the skill lacks any capabilities (such as file-writing or network access) that could be exploited via this vector.
  • Ingestion points: CONTEXT.md (referenced in SKILL.md).
  • Boundary markers: None explicitly defined in the instructions.
  • Capability inventory: None; the skill is declarative and does not include scripts or tool-use permissions.
  • Sanitization: None required as the skill does not perform actions based on the ingested content beyond linguistic alignment.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 01:08 PM
Security Audit — agent-trust-hub — tdd