vja-vikunja
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the 'vja' command-line interface to interact with a Vikunja server. This execution is limited to task management commands and is the core functionality of the skill.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it processes untrusted data from task contents.
- Ingestion points: 'vja ls' and 'vja show' commands in SKILL.md.
- Boundary markers: Absent; instructions do not require the agent to wrap external output.
- Capability inventory: Shell execution of 'vja' commands including task deletion ('vja delete') and editing.
- Sanitization: Absent.
Audit Metadata