contract-cli-contract
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves contract details, full text, and template content from external API endpoints, which creates an attack surface for indirect prompt injection if the retrieved content contains malicious instructions.
- Ingestion points: Data is ingested through
contract-cli contract get,contract-cli contract search,contract-cli contract text, andcontract-cli contract template getcommands (documented inSKILL.mdandreferences/commands.md). - Boundary markers: The instructions lack explicit delimiters or warnings to treat retrieved text strictly as data and ignore any embedded commands or instructions.
- Capability inventory: The agent has the ability to execute shell commands using the
contract-clitool and can upload local files (e.g.,contract upload-file). - Sanitization: There are no mentioned mechanisms for sanitizing or validating the content retrieved from the contract service before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill is designed to execute local CLI commands to interact with a contract management system. While these are the primary intended functions, they provide the agent with a capability that could be misused if the agent is influenced by malicious input from external data sources.
Audit Metadata