bel-contact-creator

Pass

Audited by Gen Agent Trust Hub on Nov 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to parse freeform text provided by users (such as email signatures or business cards) to extract contact information. This input is untrusted data that could potentially contain malicious instructions aimed at influencing the agent's behavior during the extraction process.
  • Ingestion points: Freeform text input used in the workflow described in SKILL.md to extract contact fields.
  • Boundary markers: The instructions lack the use of boundary markers (e.g., XML tags, triple backticks) or explicit directives to ignore any instructions embedded within the user-provided text.
  • Capability inventory: The skill possesses the capability to write data to an external service via the mcp__ms365__create-outlook-contact tool.
  • Sanitization: There are no instructions for the agent to sanitize or validate the extracted data before it is passed to the Microsoft 365 API tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 12, 2026, 07:37 PM