modal-function-sync
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute several local repository scripts to perform its tasks. These include shell scripts for synchronization (
scripts/local/sync_win_modal_client.sh) and Python scripts for registry validation and client generation (tools/validate_registry.py,tools/generate_modal_client.py). This is a standard workflow for this skill's intended developer use-case. - [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes untrusted user data to generate code and configuration.
- Ingestion points: User-provided descriptions of function intents, inputs, and outputs are used to implement code in
src/functions/and updatesrc/registry.py(documented in SKILL.md). - Boundary markers: The instructions lack explicit delimiters or warnings to ignore potentially malicious instructions embedded within the user's requirements.
- Capability inventory: The agent can write to the local filesystem (
src/functions/,src/registry.py,src/deploy.py) and execute local scripts as part of the synchronization and deployment process. - Sanitization: No sanitization or validation of the user-provided function logic is specified before it is integrated into the codebase.
Audit Metadata