swift-code-review

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to run the swiftlint command-line utility on the source code paths provided in the review scope (SKILL.md).
  • [EXTERNAL_DOWNLOADS]: Reference documentation links point to sosumi.ai, a third-party site hosting Swift and Apple framework documentation that is not an official vendor source (references/common-mistakes.md, references/concurrency.md, references/error-handling.md, references/observation.md).
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze untrusted code and diffs from external sources, which constitutes an attack surface for indirect prompt injection. 1. Ingestion points: Swift source files and git diffs provided by the user for review (SKILL.md). 2. Boundary markers: There are no explicit instructions for the agent to use delimiters or ignore instructions embedded within code comments or strings. 3. Capability inventory: The agent has the capability to execute shell commands via the swiftlint tool (SKILL.md). 4. Sanitization: The instructions do not define any sanitization or filtering of the input code before analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 11:14 AM
Security Audit — agent-trust-hub — swift-code-review