sb-inventory

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source code from the project's 'src' and 'app' directories to generate audit reports.
  • Ingestion points: The inventory-project.sh, extract-component-usage.sh, and token-usage.py scripts read all component definitions, JSX call sites, and CSS files within the scanned project directories.
  • Boundary markers: No explicit markers are used to isolate content read from source files, though the analysis is performed via regex and static parsing rather than LLM execution.
  • Capability inventory: The skill uses shell commands and Python to scan the filesystem and write JSON data to the .storybook/ directory.
  • Sanitization: No sanitization is performed on the content of the files read during analysis before including extracted metadata in the resulting JSON reports.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 01:16 PM
Security Audit — agent-trust-hub — sb-inventory