ln-62-repository-publisher
Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to discover and run native validation commands found within the target repository. This creates an execution surface for local scripts and CLI tools as part of the validation and publication workflow.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it reads and adheres to instructions, release rules, and policies found in the repository files, which are external data sources that could be used to manipulate agent behavior.
- Ingestion points: Repository documentation, release rules, branch policies, and file diffs.
- Boundary markers: The skill does not implement specific delimiters or 'ignore' instructions for the repository-resident data it ingests.
- Capability inventory: Access to Git CLI, local shell execution for validation commands, and network capabilities for pushing to remotes and interacting with hosting APIs.
- Sanitization: No validation or sanitization of instructions found within the repository content is performed before the agent acts on them.
Audit Metadata