openviking
Pass
Audited by Gen Agent Trust Hub on Mar 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill requires the agent to execute shell commands (
ov) and manage a background server (openviking-server). It also involves creating and writing to local configuration files (e.g.,~/.openviking/ovcli.conf). - [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install or update the
openvikingPython package and provides commands to download external code repositories from URLs for indexing. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and searches data from external repositories that could contain hidden instructions targeting the agent.
- Ingestion points: Remote repository URLs and local paths processed via the
ov add-resourcecommand as described in SKILL.md. - Boundary markers: None identified in the skill instructions to separate indexed code from system prompts.
- Capability inventory: Access to the shell (
bashtool), file system (read/write), and background process management as documented in SKILL.md. - Sanitization: No evidence of input validation or sanitization for the content being indexed.
Audit Metadata