swift-code-review

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted Swift source code and project manifests, which serves as a surface for malicious instructions to be embedded in data processed by the agent.
  • Ingestion points: The workflow in SKILL.md requires the agent to read file changes, surrounding contracts, callers, and package manifests.
  • Boundary markers: The skill lacks explicit instructions or delimiters to isolate the ingested code from the agent's operational instructions.
  • Capability inventory: The workflow instructs the agent to 'reproduce' defects, which may involve executing code or shell commands if the execution environment provides these tools.
  • Sanitization: No sanitization, escaping, or validation of the external code content is specified in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 10:32 AM
Security Audit — agent-trust-hub — swift-code-review