order-manager

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses the WebFetch tool to retrieve order data from the KyberSwap Limit Order API (https://limit-order.kyberswap.com/read-ks/api/v1/orders). This is a vendor-owned resource used for the skill's primary functionality.
  • [COMMAND_EXECUTION]: The skill executes python3 -c shell commands to perform arithmetic conversions (e.g., wei to human-readable units) using data variables extracted from the external API response.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted data from an external API and incorporates it into subsequent agent actions.
  • Ingestion points: Data is ingested via WebFetch GET requests to limit-order.kyberswap.com in SKILL.md.
  • Boundary markers: There are no explicit delimiters or boundary instructions provided to the agent to treat the API response as untrusted data.
  • Capability inventory: The skill uses python3 for mathematical operations, which involves executing code derived from API data.
  • Sanitization: The instructions do not specify any validation or sanitization for the fields retrieved from the API (such as makingAmount or makerAssetDecimals) before they are used in shell commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 04:45 AM