Skills
skills/naodeng/awesome-qa-skills/requirements-analysis/Gen Agent Trust Hub

requirements-analysis

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The Python scripts in the scripts/ directory utilize subprocess.call to delegate format conversion tasks to internal scripts convert_formats.py and parse_formats.py. These executions are limited to local Python invocation and do not expose the system to arbitrary shell command injection.
  • [PROMPT_INJECTION]: The skill processes untrusted requirement data via the prompt in prompts/requirements-analysis.md. Evidence: (1) Ingestion point: requirements, stories, and AC in prompts/requirements-analysis.md. (2) Boundary markers: Absent. (3) Capabilities: Filesystem read/write and script execution within the scripts/ folder. (4) Sanitization: Absent. The risk of indirect prompt injection is inherent to the skill's primary analysis task and no malicious behavior was observed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 11:49 AM