setup-mabza-skills
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands using
git,gh(GitHub CLI), andglab(GitLab CLI) to discover repository remotes, configuration, and manage issue tracking data. - [INDIRECT_PROMPT_INJECTION]: The skill establishes workflows that ingest untrusted data from external sources, creating a potential vulnerability surface.
- Ingestion points: The configuration instructs subsequent operations to read content from GitHub issues and PRs (
gh issue view), GitLab issues and MRs (glab issue view), and local user-controlled Markdown files in the.scratch/directory. - Boundary markers: There are no explicit instructions or delimiters defined to isolate untrusted content from external sources from the agent's internal instruction set.
- Capability inventory: The skill and its generated configurations use system commands (
git,gh,glab) and perform file system modifications across the repository (AGENTS.md,docs/,.agents/feedback/). - Sanitization: The instructions do not specify any sanitization, validation, or escaping protocols for data retrieved from issue trackers or local files before it is processed by the agent.
Audit Metadata