kmcp-dev-bugfix-ship

Pass

Audited by Gen Agent Trust Hub on May 20, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines a process that ingests untrusted data from bug reports, creating a surface for indirect prompt injection.
  • Ingestion points: Data is read from reports/mcp-bug-*.md or user-pasted content.
  • Capability inventory: The skill executes shell commands (npm run dev:deploy, npm run dev:test, gh pr checks) and modifies project files.
  • Boundary markers: The instructions lack explicit delimiters to separate untrusted report content from the agent's instructions.
  • Sanitization: No input sanitization is specified for the bug reports, though the skill requires redacting secrets in output logs.
Audit Metadata
Risk Level
SAFE
Analyzed
May 20, 2026, 07:40 AM
Security Audit — agent-trust-hub — kmcp-dev-bugfix-ship