iblai-vibe-ops-upgrade

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches content from raw.githubusercontent.com (a well-known service) for both the SDK and vibe skills CHANGELOG files. These resources are associated with the skill's author (iblai).
  • [COMMAND_EXECUTION]: The skill executes package management commands including pnpm update, npm install, and npx skills add to perform the upgrade. It also runs pnpm typecheck and node -p for version detection and verification.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8).
  • Ingestion points: Fetches external CHANGELOG data via curl from GitHub in SKILL.md.
  • Boundary markers: None present; the external data is piped directly to the agent's context for summarization.
  • Capability inventory: The skill has the ability to execute shell commands (npm, pnpm, npx) and modify the local filesystem (package updates).
  • Sanitization: No sanitization or filtering is applied to the fetched text before the agent summarizes it.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 01:01 PM
Security Audit — agent-trust-hub — iblai-vibe-ops-upgrade