glab-workitems
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the use of the
glabCLI tool to perform work item operations, including creation, listing, updating, and deletion within GitLab repositories and groups. - [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes external work item data (such as titles and descriptions) from GitLab, which presents a surface for instructions embedded in that data to manipulate the agent. \n
- Ingestion points: Output from the
glab work-items listcommand as documented inSKILL.mdandreferences/commands.md. \n - Boundary markers: The skill does not provide or suggest delimiters to separate retrieved work item content from other agent instructions. \n
- Capability inventory: The skill possesses the capability to modify or delete planning objects in GitLab through
glab work-items updateandglab work-items delete. \n - Sanitization: There is no evidence of sanitization or validation steps for the content ingested from GitLab.
Audit Metadata