uipath-project-boundaries

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection.
  • Ingestion points: The skill ingests and inventories "solution projects, libraries, coded packages, shared configuration, test projects, [and] runtime resources" from the repository (SKILL.md).
  • Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions potentially embedded within these untrusted files.
  • Capability inventory: The skill has the capability to run "repository-native analyzers, scripts, package rules, solution validation, or CI checks" (SKILL.md), creating a path for malicious instructions in data to trigger unintended actions.
  • Sanitization: No sanitization or filtering logic is present to validate the content of the project files before the agent processes them.
  • [COMMAND_EXECUTION]: The skill workflow involves executing various local commands and scripts.
  • Evidence: The skill instructs the agent to "Implement checks" using "repository-native analyzers, scripts, package rules, solution validation, or CI checks" (SKILL.md). This requires the agent to execute tools found within the local development environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 04:38 PM
Security Audit — agent-trust-hub — uipath-project-boundaries