format-teams-message

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands (cat, pandoc) to manage message content and conversion using temporary files.
  • [COMMAND_EXECUTION]: It utilizes osascript to interface with macOS system APIs for clipboard manipulation, specifically targeting the public.html flavor required for Teams formatting.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill uses local temporary storage (/tmp/) for processing text. Analysis confirms no access to sensitive files, credentials, or network exfiltration patterns.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: Ingests user-supplied text or content generated by the write-in-my-voice skill in SKILL.md.
  • Boundary markers: Uses shell HEREDOC with a quoted delimiter (<< 'EOF') which prevents the shell from performing variable expansion or command substitution on the message content.
  • Capability inventory: Capabilities are limited to file writing, pandoc conversion, and clipboard access via osascript as defined in SKILL.md.
  • Sanitization: Content is treated as literal text during the file writing phase, providing protection against basic command injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 09:16 AM
Security Audit — agent-trust-hub — format-teams-message