swift-clean-functions

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided Swift code or file paths, which introduces a vulnerability surface where malicious instructions could be embedded in the code to influence the agent's behavior.\n
  • Ingestion points: The $ARGUMENTS variable and file contents accessed through the Read tool in SKILL.md serve as the primary entry points for untrusted data.\n
  • Boundary markers: The skill does not implement delimiters or provide instructions to the agent to ignore any embedded directives within the analyzed code.\n
  • Capability inventory: The skill is granted access to the Read, Edit, Bash, Glob, and Grep tools, allowing for broad file system access and modification.\n
  • Sanitization: There is no evidence of input validation or sanitization of the Swift code before it is analyzed and refactored by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 01:40 PM
Security Audit — agent-trust-hub — swift-clean-functions