systems-architecture

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill analyzes external repository content and documentation, which constitutes an indirect prompt injection surface. Maliciously crafted files within a repository could attempt to subvert the agent's instructions while it is performing its architectural analysis.
  • Ingestion points: Processes repository files and lifecycle documentation using tools like read/readFile and search (SKILL.md).
  • Boundary markers: Absent. The instructions do not provide delimiters or specific directives to ignore embedded instructions found within analyzed files.
  • Capability inventory: The agent has access to powerful tools including vscode/runCommand, edit/editFiles, edit/createFile, and edit/createDirectory (SKILL.md frontmatter).
  • Sanitization: Absent. No sanitization or validation logic is defined for the content extracted from the files being analyzed.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 03:33 AM