uipath-coded-apps

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the uip CLI and npm to perform operations such as building (npm run build), packaging (uip codedapp pack), and deploying (uip codedapp deploy). These commands are necessary for the skill's primary function of managing coded applications.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the download of project files from Studio Web (uip codedapp pull) and references the @uipath/codedapp-tool npm package as a prerequisite. These downloads originate from the vendor's official services and registries.
  • [DATA_EXFILTRATION]: Local source code and build artifacts are uploaded to UiPath cloud environments (uip codedapp push, uip codedapp publish). This movement of data is the intended and primary purpose of the skill for cloud-based collaboration and deployment.
  • [PROMPT_INJECTION]: The skill handles project files pulled from external cloud projects or local directories, which represents a surface for indirect prompt injection if those files contain malicious instructions.
  • Ingestion points: Files are synchronized between the local machine and Studio Web using push and pull commands.
  • Boundary markers: The instructions do not define explicit delimiters or warnings for the agent to ignore instructions embedded within the processed code files.
  • Capability inventory: The skill uses Bash to execute CLI tools and has the ability to read and write files within the project directory.
  • Sanitization: There is no mention of content filtering or sanitization for the files being synchronized.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 04:10 PM