update-mr-desc
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the GitLab CLI (
glab), a well-known utility, to retrieve merge request diffs and update descriptions. This is the primary function of the skill and follows standard practices. - [PROMPT_INJECTION]: The skill is exposed to potential indirect prompt injection because it processes untrusted merge request diffs.
- Ingestion points: Diff content from
glab mr diffin the 'Getting the diff' section. - Boundary markers: No specific boundary markers are used to isolate the diff content from instructions.
- Capability inventory: The skill can execute shell commands (
glab mr update) to modify remote MR descriptions. - Sanitization: No sanitization is applied to the diff text before it is summarized by the model.
- Note: This risk is mitigated by the mandatory user confirmation requirement ('Updating the description' section), which prevents automated execution of potentially injected instructions without oversight.
Audit Metadata