parcel-tracking

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by ingesting and processing untrusted external data.
  • Ingestion points: The skill searches for and reads the contents of emails in the user's Gmail account and scrapes data from third-party carrier tracking websites.
  • Boundary markers: There are no explicit instructions or delimiters used to separate untrusted external content from the agent's core logic, nor are there warnings to ignore embedded instructions within that content.
  • Capability inventory: The skill utilizes high-privilege capabilities including Gmail access (via MCP or CLI tools), web scraping, and browser automation.
  • Sanitization: The instructions do not specify any validation or sanitization of the data retrieved from emails or websites before it is used to generate the final response.
  • [COMMAND_EXECUTION]: To retrieve parcel information, the skill instructions include the use of command-line interface tools like gws (e.g., gws gmail), which involves the execution of local system commands to access user data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 11:43 PM