afrexai-email-to-calendar

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes external, untrusted content from emails. \n
  • Ingestion points: Untrusted data enters the context via forwarded emails, inbox scans, or user-pasted text as described in SKILL.md.\n
  • Boundary markers: The instructions lack explicit delimiters (like XML tags or block markers) to separate the agent's instructions from the untrusted email content.\n
  • Capability inventory: The skill has the capability to execute shell commands via osascript and the gog utility.\n
  • Sanitization: There is no evidence of sanitization, filtering, or validation of the email content before it is processed by the agent.\n- [COMMAND_EXECUTION]: The skill instructions direct the agent to execute specific shell commands to interact with calendar applications.\n
  • Evidence: SKILL.md Section 4 provides shell commands for gog calendar create and osascript to interface with system calendars.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 04:17 PM