analyze-issue

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by processing external, untrusted content from GitHub issues.
  • Ingestion points: The skill retrieves GitHub issue content via the gh issue:* tool and reads local project files for context.
  • Boundary markers: Absent. The prompt does not define delimiters or provide instructions to the agent to ignore embedded commands within the fetched issue data.
  • Capability inventory: The skill possesses Write access to the filesystem (allowing it to create or modify files in ./specs/issues/) and can execute specific gh CLI commands.
  • Sanitization: Absent. The skill does not validate or filter the contents of the GitHub issue before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 03:49 AM