glab-variable
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and processes untrusted data from GitLab environments and external files.\n
- Ingestion points: Untrusted data enters the agent context through the
glab variable list,glab variable get, andglab variable importcommands (referencing SKILL.md and references/commands.md).\n - Boundary markers: No delimiters or instructions are provided to the agent to treat the content of CI/CD variables as potentially hostile or to ignore embedded instructions.\n
- Capability inventory: The skill allows for the creation, modification, and deletion of variables via the
glabCLI tool, providing a wide range of actions that could be influenced by injected instructions.\n - Sanitization: There is no evidence of data sanitization or validation performed on variable values or keys before they are presented to the agent.
Audit Metadata