skills/sones3/skills/start-next-issue/Gen Agent Trust Hub

start-next-issue

Pass

Audited by Gen Agent Trust Hub on Apr 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill defines a benign instructional process for software development task coordination and design discussions.
  • [SAFE]: No evidence of hardcoded credentials, sensitive file access, or network exfiltration patterns was found.
  • [PROMPT_INJECTION]: The skill features a surface for indirect prompt injection by reading external data from GitHub issues.
  • Ingestion points: Reviews closing comments and issue summaries from GitHub (SKILL.md).
  • Boundary markers: Absent; the instructions do not include delimiters or specific warnings to ignore instructions potentially embedded inside issue content.
  • Capability inventory: Codebase exploration (file system read access) and issue status updates.
  • Sanitization: Absent; external content from issues is used directly to inform the agent's recommendations and discussion flow.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 27, 2026, 10:53 AM