extract-saas-design

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection due to its core function of ingesting and analyzing untrusted codebase content.
  • Ingestion points: The agent reads project files including .tsx, .jsx, .css, and configuration files from the local workspace to identify styling patterns and tokens.
  • Boundary markers: The skill instructions lack specific requirements for using delimiters or defensive prompts to isolate and ignore potentially malicious instructions embedded in code comments or data within the analyzed files.
  • Capability inventory: The skill uses system commands like grep and find to access file contents and produces multiple output markdown files in the .design-soul/ directory.
  • Sanitization: There is no defined process for sanitizing or validating the extracted content before it is interpolated into the design documentation templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 04:49 PM