new-api-support

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection via the <entity_name> argument.
  • Ingestion points: The <entity_name> input enters via the skill's argument hint and is used in SKILL.md.
  • Boundary markers: None present; the argument is not wrapped in delimiters or safety instructions.
  • Capability inventory: The skill executes shell commands (find, grep) and Swift tests (swift test, xcodebuild).
  • Sanitization: None present; the input is used directly in string interpolation for shell execution.
  • [COMMAND_EXECUTION]: User-provided input is interpolated into shell commands, creating a risk of command injection.
  • Evidence: Step 1 uses grep -r "<entity_name>" and Step 4 uses swift test --filter "testInvestigate_<EntityName>". A malicious user could provide a crafted string to execute arbitrary code on the developer's machine.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 12:15 PM