tasks-axi

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches the tasks-axi package from the NPM registry to provide its core functionality.
  • [REMOTE_CODE_EXECUTION]: The skill executes the downloaded tasks-axi package using the npx utility.
  • [COMMAND_EXECUTION]: The instructions utilize the npx -y flag, which allows the agent to install and run the package without interactive confirmation prompts.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external workspace files which may contain untrusted data. • Ingestion points: The backlog.md and .tasks.toml files in the workspace. • Boundary markers: No explicit delimiting or instruction-ignoring warnings are implemented in the prompt templates. • Capability inventory: The skill enables the agent to perform file system modifications and shell command execution. • Sanitization: No validation or sanitization logic for the backlog content is defined in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 03:03 AM