stacked-prs

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes standard Git commands for version control and workflow management. It appropriately recommends the use of --force-with-lease to prevent accidental history overrides.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines templates for pull request metadata that incorporate user-provided content.
  • Ingestion points: User-provided feature names and stack details in SKILL.md.
  • Boundary markers: Absent; user input is directly included in PR templates.
  • Capability inventory: Git CLI operations and remote repository API interactions.
  • Sanitization: Relies on the host environment's execution guardrails.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 12:54 PM
Security Audit — agent-trust-hub — stacked-prs