new-module

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using uv run for code linting and testing in Step 8.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by interpolating user-provided input into shell commands.
  • Ingestion points: The module name is provided via the $ARGUMENTS variable in SKILL.md.
  • Boundary markers: The skill lacks delimiters or instructions to treat the module name strictly as data, leaving it exposed to the execution context.
  • Capability inventory: The skill has the capability to execute shell commands via the uv run tool in SKILL.md.
  • Sanitization: The module name is used directly to construct file paths and shell commands in Step 8 without any validation, escaping, or sanitization, creating a risk of command injection if a malicious name is supplied.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 03:23 PM
Security Audit — agent-trust-hub — new-module