modal
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection through its web scraping and OCR examples in
references/examples.md. These patterns allow an attacker to embed malicious instructions in web pages or images that are then processed and included in the agent's context. - Ingestion points: The
scrape_urlfunction (line 91) fetches arbitrary web content viahttpx, and theocr_pagefunction (line 160) extracts text from images viapytesseract. - Boundary markers: There are no boundary markers or instructions to delimiters used when the extracted text is returned to the agent.
- Capability inventory: The skill has access to sensitive capabilities including network requests (
httpx), file system writes (modal.Volume), and subprocess execution (subprocess.runinreferences/gpu.md). - Sanitization: There is no evidence of sanitization, filtering, or validation performed on the ingested external data before it is presented to the agent.
- [COMMAND_EXECUTION]: The skill facilitates remote and local command execution as part of its core functionality. This includes using the Modal CLI for
modal run,modal deploy, andmodal volumeoperations. Additionally, the skill's build system (.run_commands()) and GPU training examples (subprocess.run) allow for arbitrary shell command execution in both local and remote environments. - [EXTERNAL_DOWNLOADS]: The skill installs the
modalPython package and dependencies viauvorpip. It also facilitates the download of container images from registries and model weights from external sources like Hugging Face (e.g.,snapshot_downloadinreferences/images.md) during the image build process. - [DATA_EXFILTRATION]: The skill manages highly sensitive credentials, specifically
MODAL_TOKEN_IDandMODAL_TOKEN_SECRET, as well as general application secrets viamodal.Secret. The ability to transfer data between the local machine and cloud volumes (modal volume put/get) creates a pathway for potential data exfiltration if the agent is manipulated into moving sensitive files.
Audit Metadata