to-issues

Pass

Audited by Gen Agent Trust Hub on Nov 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted data which could contain malicious instructions designed to manipulate the agent's behavior during ticket creation or PRD synthesis.\n
  • Ingestion points: The skill reads repository files, conversation history, and existing issue tracker content (bodies and comments) as seen in SKILL.md and references/to-prd.md.\n
  • Boundary markers: The agent uses markdown templates (assets/issue-template.md, assets/to-prd-prd-template.md) to structure its output, but the instructions do not specify the use of delimiters or 'ignore' instructions for the source data being processed.\n
  • Capability inventory: The skill is capable of reading repository content and publishing issues to external tracking systems.\n
  • Sanitization: There is no explicit instruction to sanitize or escape data gathered from external sources before interpolation into prompts or publication.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 15, 2026, 05:09 PM