add-workiq-tools

Pass

Audited by Gen Agent Trust Hub on Oct 12, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • Indirect Prompt Injection Surface: The skill processes local project files and output from the a365 CLI to determine the appropriate configuration and code updates. This represents a potential surface for indirect prompt injection.
  • Ingestion points: Project manifests (package.json, requirements.txt, .csproj), configuration files (.a365-workspace-detection.local.json), and CLI output (a365 develop list-available).
  • Boundary markers: Absent; the skill does not use specific delimiters to isolate external data from its instructions.
  • Capability inventory: Utilizes the Bash tool for command execution and the Edit and Write tools for modifying source code and configuration files.
  • Sanitization: Absent; the skill does not explicitly describe sanitization or validation of the ingested data before it is used in logic or code generation.
  • Command Execution: The skill uses the Bash tool to automate several development tasks.
  • Activity: Executes a365 CLI commands for tool discovery and token management, as well as package manager commands (npm, pip, dotnet) for environment setup.
  • External Software Installation: The skill automates the installation of various library extensions from official registries.
  • Activity: Installs software packages from the @microsoft namespace and official Microsoft repositories. These are recognized as official vendor resources used for their intended purpose.
  • Development Secret Management: The skill provides guidance on managing authentication tokens for local development.
  • Activity: Instructions for storing BEARER_TOKEN values in .env files or project configuration settings follow standard security practices for secret management during development.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 12, 2026, 09:58 PM