dart-package-skill-creator
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves inspecting and analyzing untrusted external repository content to generate or audit agent instructions.
- Ingestion points: The skill instructions direct the agent to read
pubspec.yaml,README.md,CHANGELOG.md, and source files within thelib/,example/, andtest/directories of a project. - Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from being influenced by malicious instructions embedded within these repository files during the analysis phase.
- Capability inventory: The skill includes instructions for creating and modifying files in the
skills/directory and suggests the use of CLI tools likedart run skills@for project management. - Sanitization: The skill lacks specific guidelines for sanitizing or validating external repository content before incorporating that information into prescriptive agent rules.
Audit Metadata