vike
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted blockchain data and wallet labels from external sources, which could potentially contain malicious instructions.
- Ingestion points: Data retrieved via the vike-data CLI and MCP tools (e.g., wallet labels, transaction history) as described in SKILL.md.
- Boundary markers: None specified; the instructions do not require the agent to use delimiters or ignore instructions within the retrieved data.
- Capability inventory: The agent can execute CLI commands and perform network operations to vendor-specified endpoints.
- Sanitization: Not mentioned; the skill does not specify any sanitization or validation of the ingested external data.
- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the vendor's official command-line interface tool.
- Evidence: The instruction
npm install -g @vike-io/clifor the @vike-io/cli package. - [COMMAND_EXECUTION]: The functionality of the skill relies on the execution of the
vike-datautility on the host system to fetch on-chain data.
Audit Metadata