ruff-recursive-fix

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill dynamically constructs and executes shell commands by interpolating user-supplied inputs such as ruff_runner, target_path, and various rule override strings (e.g., rules_select, rules_ignore). If these inputs contain shell metacharacters (e.g., semicolons, pipes, or backticks), it could lead to the execution of arbitrary, unauthorized commands on the host environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill lacks explicit sanitization or boundary markers for untrusted data ingested from the user. This creates a vulnerability where malicious inputs could be used to override the intended behavior of the agent during the command construction phase.
  • Ingestion points: Inputs ruff_runner, target_path, rules_select, rules_ignore, extend_select, and extend_ignore are sourced from the user/environment.
  • Boundary markers: None identified; inputs are interpolated directly into shell templates.
  • Capability inventory: The agent is authorized to execute shell commands via the resolved ruff_cmd (e.g., ruff check, ruff format).
  • Sanitization: There are no instructions provided to validate or escape shell characters before the command is executed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 05:26 PM
Security Audit — agent-trust-hub — ruff-recursive-fix