swift-code-review
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions define a legitimate and security-conscious workflow for auditing Swift code. It specifically directs the agent to check for retain cycles, concurrency issues, and secret exposure in the code being reviewed.
- [INDIRECT_PROMPT_INJECTION]: As the skill is designed to ingest and analyze external, potentially untrusted Swift source code, it possesses an inherent attack surface for indirect prompt injection. This risk is managed by the skill's primary focus on evidence-backed tracing and reproduction.
- Ingestion points: Processes source files from a code repository as specified in the SKILL.md workflow.
- Boundary markers: The workflow relies on the agent's ability to distinguish between its instructions and the data (code) it is analyzing, without specifying explicit delimiters.
- Capability inventory: The skill instructs the agent to statically trace and reproduce defects, which may involve using file-reading and shell-execution tools available to the agent platform.
- Sanitization: The instructions do not define specific sanitization or filtering for the code being reviewed, relying on the agent's internal safety guardrails.
Audit Metadata