iblai-vibe-agent-skills

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to download an environment configuration template from the vendor's official GitHub repository.
  • Evidence: curl -o iblai.env https://raw.githubusercontent.com/iblai/vibe/refs/heads/main/iblai.env found in SKILL.md.
  • [INDIRECT_PROMPT_INJECTION]: The skill implements a system for managing agent instructions, creating an attack surface where malicious input could influence agent behavior.
  • Ingestion points: User input in the 'Instruction' field within the 'New/Edit Skill' dialog described in SKILL.md.
  • Boundary markers: No explicit boundary markers or 'ignore embedded instructions' warnings are documented for the interpolation of these instructions.
  • Capability inventory: The agent uses these instructions to perform tasks such as web research and code review as described in the skill overview.
  • Sanitization: The documentation does not specify any sanitization or validation protocols for the instructions entered by users.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 12:48 PM
Security Audit — agent-trust-hub — iblai-vibe-agent-skills