skills/mholtzscher/skills/mstack/Gen Agent Trust Hub

mstack

Pass

Audited by Gen Agent Trust Hub on Nov 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, which could contain malicious instructions designed to influence the agent's behavior.
  • Ingestion points: The scripts/threads.ts and scripts/logs.ts files fetch PR review threads, comments, and CI logs from GitHub into the agent's context for triage and debugging.
  • Boundary markers: The skill includes explicit instructions in principles/boundary-discipline.md and scripts/README.md that direct the agent to treat external comments and logs as evidence or data, never as instructions.
  • Capability inventory: The skill possesses capabilities to execute gh CLI commands for repository management, perform local file writes (via scripts/decision-log.ts), and manage worktrees for code implementation.
  • Sanitization: The scripts/actions-log.ts helper includes a stripAnsi function to clean log data and truncate logic to bound the size of processed text payloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 20, 2026, 08:18 PM