gitlab-issue-picker

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute glab issue list and other glab commands. This is the primary function of the skill to fetch local project data from GitLab.
  • [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection. It ingests untrusted data (issue titles and descriptions) via the glab CLI and processes it using the agent's reasoning capabilities.
  • Ingestion points: Untrusted data enters the context from the glab issue list --output json command output in SKILL.md.
  • Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands within the ingested issue content.
  • Capability inventory: The skill has access to the Bash tool, allowing for potential command execution if an injected instruction is followed by the agent.
  • Sanitization: The skill does not perform sanitization or filtering on the retrieved issue content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 07:50 PM
Security Audit — agent-trust-hub — gitlab-issue-picker