windows-release-pipeline

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external configuration and build files, creating a potential surface for indirect prompt injection if an attacker compromises those files.
  • Ingestion points: The agent is instructed to read and modify project files such as .github/workflows/*.yml and PyInstaller .spec files.
  • Boundary markers: The skill does not define specific delimiters or warnings to ignore embedded instructions within these processed files.
  • Capability inventory: The skill grants the agent the ability to use Read, Edit, Write, and Bash to manage the release pipeline.
  • Sanitization: The skill focuses on standard CI/CD logic and does not include specific sanitization or filtering logic for the content of the processed files.
  • [COMMAND_EXECUTION]: The skill provides templates for executing standard build and signing tools including pyinstaller, signtool, AzureSignTool, and Compress-Archive. These commands are appropriate for the skill's stated purpose of automating software delivery pipelines.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 04:16 AM