ida-domain-scripting
Fail
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill generates Python code based on user requests and executes it using
uv run python. This mechanism for dynamic script execution is a core feature but constitutes a significant security risk if the generated code is malicious. - [COMMAND_EXECUTION]: The
run.pyandsetup.pyscripts make use ofsubprocess.runto execute system commands, including the generated analysis scripts, git commands for cloning, and environment setup utilities. - [EXTERNAL_DOWNLOADS]: The
setup.pyscript downloads theida-domainlibrary from the vendor's GitHub repository and suggests the official installation method for theuvtool fromastral.sh. - [PROMPT_INJECTION]: The skill analyzes external binary files, exposing it to indirect prompt injection. 1. Ingestion points: Extracting strings and pseudocode from binaries via
db.stringsanddb.functions. 2. Boundary markers: No delimiters are used to wrap data from the analyzed binary to prevent interpretation as instructions. 3. Capability inventory: Full access to execute shell commands and write to the file system through generated scripts. 4. Sanitization: No validation or filtering is performed on data retrieved from the target binary before processing.
Recommendations
- HIGH: Downloads and executes remote code from: https://astral.sh/uv/install.sh - DO NOT USE without thorough review
Audit Metadata