spiral-html

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides local automation via shell scripts (init.sh and audit.sh). These scripts use standard system utilities including git, python3, grep, and awk to manage project initialization and verify structural integrity of the repository. All operations are local and consistent with the skill's purpose.
  • [EXTERNAL_DOWNLOADS]: Documentation templates for dependency management reference the author's official GitHub repositories (Randroids-Dojo/VibeKit) for the purpose of checking for updates. These references target the vendor's own infrastructure and are documented neutrally as part of the intended functionality.
  • [PROMPT_INJECTION]: The skill establishes a workflow where an AI agent is instructed to read from various documentation files within the repository (e.g., OPEN_QUESTIONS.html, FOLLOWUPS.html). While this creates a surface for potential indirect prompt injection if external actors modify these files, the skill itself contains no malicious instructions or bypass attempts.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 02:59 PM
Security Audit — agent-trust-hub — spiral-html