publish

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses git, gh (GitHub CLI), npm, and bun to perform repository operations, trigger CI/CD workflows, and verify package states. It specifically executes a local script script/generate-changelog.ts for documentation generation.
  • [EXTERNAL_DOWNLOADS]: Interacts with GitHub and the npm registry to manage release versions and verify the deployment of multiple platform-specific packages.
  • [DATA_EXFILTRATION]: Uses the agent-discord tool to announce releases to a specific Discord channel. This involves accessing Discord authentication context to perform the announcement as part of the automated workflow.
  • [PROMPT_INJECTION]: Ingests potentially untrusted data from git logs and repository metadata to generate release narratives. While this presents an indirect prompt injection surface, it is a standard part of the automated release process.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 02:35 PM
Security Audit — agent-trust-hub — publish