prd-to-issues

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external PRD content retrieved from GitHub issues via the gh issue view command. This creates a surface for indirect prompt injection where instructions hidden in the PRD could influence the agent's behavior.
  • Ingestion points: Data enters the context via gh issue view in SKILL.md.
  • Boundary markers: The instructions include a 'Security & Multi-Agent Hygiene' section advising that external data be treated as hostile, though specific text delimiters for the PRD content are not explicitly defined in the template.
  • Capability inventory: The agent can create issues (gh issue create), execute terminal commands (rtk npm test), and perform cognitive tasks via MCP loops (sequentialthinking, context7).
  • Sanitization: The skill explicitly instructs the agent to redact secrets and PII before sharing context.
  • [COMMAND_EXECUTION]: The skill uses the GitHub CLI and a terminal proxy for operational tasks.
  • Evidence: Commands include gh issue view, gh issue create, and the rtk execution proxy for running tests (e.g., rtk npm test) as described in the 'Iron Law of Execution' section of SKILL.md.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 07:35 AM
Security Audit — agent-trust-hub — prd-to-issues