polymarket-brier
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input in the form of a Polymarket address, username, or URL which is then interpolated directly into a shell command.
- Ingestion points: The
{ADDRESS}variable in thecurlcommand withinSKILL.md. - Boundary markers: Absent. There are no instructions to the agent to validate or sanitize the input format before execution.
- Capability inventory: The skill uses
Bashwithcurl,Read,Write, andEdittools. - Sanitization: Absent. The instructions do not specify escaping or validation logic to prevent a malicious user from providing input that escapes the
curlcommand (e.g., via shell metacharacters). - [EXTERNAL_DOWNLOADS]: The skill fetches data from
data-api.polymarket.com. This is a well-known service associated with the skill's stated purpose, and the data being accessed is public trading information. - [COMMAND_EXECUTION]: The skill relies on
Bashto executecurlcommands for data retrieval and potentially for post-processing logic described in the execution steps.
Audit Metadata