skills/akhy/agent-skills/vikunja-vja/Gen Agent Trust Hub

vikunja-vja

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on the vja CLI and jq to manage tasks. It also demonstrates the use of xargs to perform bulk operations, which involves constructing shell commands from task IDs fetched from the external service.
  • [EXTERNAL_DOWNLOADS]: The skill metadata specifies the installation of external dependencies vja (via uv) and jq (via brew). These downloads occur from public registries and are necessary for the skill's functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by ingesting and processing untrusted data.
  • Ingestion points: Task titles, notes, descriptions, and project names are retrieved from a remote Vikunja instance through commands like vja ls and vja show (SKILL.md).
  • Boundary markers: The skill does not define specific delimiters or instructions to treat task content as untrusted data.
  • Capability inventory: The skill has the ability to modify/delete tasks, create projects/labels, and open URLs in a browser (vja open).
  • Sanitization: No explicit sanitization or filtering of task content is described in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 12:18 AM