teams-adaptive-cards

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill instructions in SKILL.md and the reference files focus on technical implementation and design best practices. No attempts to bypass safety filters or override system instructions were found.
  • [DATA_EXFILTRATION]: No network operations or credential harvesting patterns were detected. All external links point to official Microsoft documentation or generic placeholders (example.com).
  • [REMOTE_CODE_EXECUTION]: The skill does not perform any remote script downloads or execution. It includes a local Node.js script (scripts/check-teams-card.mjs) designed for linting JSON payloads.
  • [COMMAND_EXECUTION]: The provided Node.js script is a standard CLI tool that uses built-in modules (node:fs, node:path) to read and validate local files. It does not execute arbitrary shell commands or use unsafe functions like eval().
  • [OBFUSCATION]: All instructions and code are provided in clear text. No hidden characters, Base64-encoded strings, or homoglyph substitutions were identified.
  • [SAFE]: The skill follows best practices for Microsoft Teams development, including proper transport wrapping and versioning guidance. All referenced resources are within the expected domain of the skill's purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 07:18 AM
Security Audit — agent-trust-hub — teams-adaptive-cards