acceptance-criteria-authoring

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized commands were detected. The skill consists entirely of educational material and templates for software development requirements.
  • [NO_CODE]: This skill is composed of a single markdown file containing documentation and examples; it does not ship with any executable scripts or binary files.
  • [PROMPT_INJECTION]: The skill is designed to process user-provided stories and requirements, creating a surface for indirect prompt injection. 1. Ingestion points: User story and requirement descriptions provided by the user. 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are included in the authoring templates. 3. Capability inventory: The skill utilizes Read, Write, Glob, Grep, and Task tools. 4. Sanitization: No input validation or sanitization logic is present in the provided documentation templates. This vulnerability surface is inherent to the skill's primary function of structured requirement authoring.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 06:56 AM