flutter-ci-cd
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external project data, which introduces a potential surface for indirect prompt injection from untrusted repository content.
- Ingestion points: The skill reads
pubspec.yaml, lockfiles, SDK configuration, existing pipeline files, repository scripts, and build logs from the target project. - Boundary markers: The instructions explicitly define an 'Authorization boundary' and 'Boundaries' section to separate validation from publication and restrict the scope of modification.
- Capability inventory: The skill modifies CI/CD configuration files (YAML/scripts) and orchestrates local repository commands (build, test, generate).
- Sanitization: The instructions include strict prohibitions against printing, moving, or committing signing materials or credentials, and require dry-runs before external mutations.
Audit Metadata