multi-repo-git-ops
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reads external project files to derive values for shell command interpolation, creating a potential surface for injection if project metadata is untrusted.
- Ingestion points: The agent is instructed to read configuration from
.gitmodulesand project status from_bmad-output/implementation-artifacts/sprint-status.yamland story files. - Boundary markers: There are no explicit instructions or delimiters for the agent to treat content within these files as data only and to ignore any embedded natural language instructions.
- Capability inventory: The skill uses ingested data to perform directory navigation (
cd), branch creation (git checkout -b), and repository updates across the file system. - Sanitization: The instructions do not specify validation or escaping of service names or branch names retrieved from the repository files before they are passed to shell execution templates.
- [COMMAND_EXECUTION]: The skill provides structured templates for complex shell operations, including loops and variable assignment based on the current state of the filesystem and git configuration.
Audit Metadata