skill-system-github

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on the execution of gh CLI commands to interact with GitHub services. These operations are performed within the context of the user's authenticated session and are consistent with the skill's stated purpose of repository management.
  • [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection as it processes data from external GitHub issues. Ingestion points: scripts/manage-issues.md (retrieving issue lists and details for duplicate detection). Boundary markers: Absent in the instructions. Capability inventory: proc.exec (gh commands for writing issues, labels, and workflows) and fs.write (modifying local workflow and template files). Sanitization: The scripts do not explicitly define sanitization or escaping logic for the content retrieved from issue titles or bodies before the agent processes them.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 12:55 AM