release
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes several standard command-line tools including
git,gh(GitHub CLI), andcargoto manage the local development environment, fetch repository state, and verify build artifacts. - [REMOTE_CODE_EXECUTION]: The skill's primary function is to trigger remote GitHub Actions workflows (
release.yml,gateway-update.yml,release-announce.yml) within the officialfreenet/freenet-corerepository. This is an intended and authorized use of the platform's CI/CD capabilities for project maintenance. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from git commit messages via
git logto generate changelogs. While commit messages are external inputs that could theoretically contain malicious instructions, the risk is mitigated by the skill's requirement for the agent to present the changelog to the user and obtain explicit confirmation before proceeding with the release.
Audit Metadata