prd-to-issues

Warn

Audited by Snyk on Mar 4, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 1.00). The SKILL.md "Locate the PRD" step explicitly tells the agent to fetch a GitHub issue with gh issue view <number> and "read and internalize the full PRD content (with all comments)," which means it ingests user-generated, public third-party content from GitHub that directly informs subsequent issue-creation decisions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.80). The skill fetches the PRD at runtime from a GitHub issue URL (e.g., https://github.com///issues/) using gh issue view <number>, and that fetched issue content is read and used to drive the agent's prompts/instructions, so the GitHub issue URL is a runtime external dependency that can control the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 04:58 AM