groundwork-scaffold-interface

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection because it reads and processes untrusted application code to generate documentation.
  • Ingestion points: The skill reads files from multiple directories including src/, app/, lib/, routes/, api/, controllers/, pages/, and components/ (SKILL.md).
  • Boundary markers: The instructions do not specify any delimiters or directives to ignore instructions embedded within the codebase being scanned.
  • Capability inventory: The agent performs recursive file reading across the codebase and writes the output to docs/specs/SPEC-INTERFACE.md.
  • Sanitization: There are no requirements to sanitize, escape, or validate the content extracted from the codebase before it is interpolated into the generated draft.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 04:38 PM