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

issue

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided bug reports or feature requests to draft issue content, which is a potential surface for indirect prompt injection.
  • Ingestion points: User-provided short descriptions processed in SKILL.md Workflow step 1.
  • Boundary markers: None explicitly defined for the prompt interpolation.
  • Capability inventory: Shell command execution via gh issue list and gh issue create.
  • Sanitization: The workflow strictly requires a human-in-the-loop (Workflow step 4), where the agent must present the title and body to the user for approval before execution, mitigating the risk of processing malicious instructions within the data.
  • [COMMAND_EXECUTION]: The skill uses the GitHub CLI (gh) for its primary functionality. These commands are restricted to listing and creating issues within the repository context and require user approval for the creation step.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 09:15 AM
Security Audit — agent-trust-hub — issue