vike-polymarket-markets
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the 'vike-data' CLI tool to retrieve market information. This is a vendor-owned resource provided by the author ('vike-io') and is used for its intended purpose within the specified tool constraints.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from external prediction markets (via the 'vike-data' command), which presents a potential surface for indirect prompt injection where malicious instructions could be embedded in market metadata.
- Ingestion points: Market questions, slugs, and outcome descriptions are ingested into the agent context from the 'vike-data polymarket markets' command output (SKILL.md).
- Boundary markers: Absent; the skill does not specify the use of delimiters (e.g., XML tags or triple quotes) to separate external tool output from the agent's instructions.
- Capability inventory: The skill is authorized to execute bash commands within the 'vike-data:*' namespace.
- Sanitization: Absent; no explicit sanitization, filtering, or validation of the market question strings or outcome names is defined before the data is processed by the agent.
Audit Metadata