modal
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill provides detailed instructions on using the
modalCLI tool to interact with the platform. This includes commands for resource management, app observation, and a specificmodal skills updatecommand intended to update the skill's own instructions from the vendor's infrastructure. - [EXTERNAL_DOWNLOADS]: The instructions direct the agent to fetch documentation from vendor-controlled URLs, specifically
https://modal.com/llms.txtandhttps://modal.com/llms-full.txt, to stay up-to-date with API changes. - [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest data from external URLs which creates a surface for indirect prompt injection.
- Ingestion points: Documentation URLs
https://modal.com/llms.txtandhttps://modal.com/llms-full.txtmentioned inSKILL.md. - Boundary markers: None identified; the agent is encouraged to read these files directly into context.
- Capability inventory: The agent has the capability to execute shell commands via the
modalCLI. - Sanitization: No specific sanitization or validation of the fetched documentation content is described.
Audit Metadata