skills/cniska/skills/issue/Gen Agent Trust Hub

issue

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the GitHub CLI (gh) to perform legitimate actions such as listing issues (gh issue list) and creating new ones (gh issue create). These commands are restricted to the stated purpose of the skill.
  • [PROMPT_INJECTION]: The skill processes user-provided descriptions to generate issue content. This is a potential surface for indirect prompt injection.
  • Ingestion points: User descriptions are ingested during the 'Understand the idea' workflow step in SKILL.md.
  • Boundary markers: No explicit delimiter markers are used for user input.
  • Capability inventory: The skill has the capability to execute commands via the gh tool.
  • Sanitization: No specific sanitization of the input text is mentioned.
  • Note: The risk is effectively mitigated by the mandatory rule 'Never create an issue without showing the draft to the user first', ensuring human-in-the-loop verification before execution.
  • [SAFE]: No obfuscation, data exfiltration, hardcoded credentials, or unauthorized network activity were detected in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 10:46 AM