skills/cloudvoyant/codevoyant/release/Gen Agent Trust Hub

release

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to execute semantic-release and release-it from the npm registry.
  • [COMMAND_EXECUTION]: The skill executes several shell commands to determine project state and predict version bumps.
  • Commands include git describe for tag analysis, jq for parsing package metadata, and npx for running dry-run release simulations (SKILL.md).
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external project data which could serve as a vector for indirect injection.
  • Ingestion points: Project configuration files like package.json, .releaserc, and git commit history (SKILL.md).
  • Boundary markers: Absent; the skill pipes tool output directly to the agent's context.
  • Capability inventory: Shell execution of git and npx (SKILL.md).
  • Sanitization: The skill does not explicitly sanitize the contents of commit messages or package metadata, though it uses standard tools that typically handle these formats safely.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 01:12 AM
Security Audit — agent-trust-hub — release