teams-app-manifest

Pass

Audited by Gen Agent Trust Hub on Sep 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection Surface: The skill processes external source code, configuration files, and README documentation to determine the required capabilities for a Teams app manifest. This represents a data ingestion surface where specific patterns in the analyzed files could influence the resulting manifest permissions. The skill includes design features to manage this, such as a strict authority order, schema validation, and a requirement to stop and ask the user for clarification on security-sensitive values.
  • Trusted External References: The skill utilizes official documentation and schemas from established domains to validate manifest structure and features. These references are used appropriately for technical verification.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 29, 2026, 10:36 PM