swift-concurrency-expert

Pass

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze user-supplied Swift code and compiler diagnostics to provide fixes, which introduces a vulnerability surface for indirect prompt injection. * Ingestion points: The agent is instructed to triage and capture exact compiler diagnostics and offending symbols from user-provided files as outlined in SKILL.md. * Boundary markers: There are no instructions or explicit delimiters defined to ensure the agent ignores instructions embedded within comments or string literals in the source code. * Capability inventory: The skill workflow involves applying code changes like adding 'Sendable' or '@MainActor', implying the use of file-editing or code-generation capabilities. * Sanitization: The skill does not include steps to sanitize or validate the provided code before or after modification.
  • [NO_CODE]: The skill consists exclusively of instructional Markdown files and YAML configuration, with no executable scripts, binaries, or automated installation processes included.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 5, 2026, 09:27 PM