swift-stable
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it is designed to process external repository data and then execute build commands. Ingestion points: The skill reads Package.swift and project source files (SKILL.md). Boundary markers: No explicit instructions to use boundary markers or to ignore instructions embedded within the processed source code were found. Capability inventory: The skill executes swift build and swift test commands. Sanitization: The instructions do not specify any sanitization or validation steps for the code being processed.
- [COMMAND_EXECUTION]: The skill instructions in SKILL.md explicitly direct the agent to execute shell commands (swift build and swift test) to verify implementations and behavioral failures.
Audit Metadata