fancy-locale

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions direct the agent to execute a provided shell script (scripts/set-locale.sh) using the bash interpreter. This script is used to perform file system operations based on user input.
  • [COMMAND_EXECUTION]: The scripts/set-locale.sh script programmatically modifies the local environment by copying files (cp) to overwrite SKILL.md instructions within .claude/skills, .agents/skills, and .cursor/skills directories.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to modify the execution context of other skills by swapping their instruction files (SKILL.md) with localized versions (SKILL.zh-CN.md). This creates a vulnerability surface where a malicious or compromised translation file could be used to override the behavior of multiple agent skills simultaneously.
  • Ingestion points: The script reads and copies content from *.zh-CN.md files located in the skill's installed directories.
  • Boundary markers: None; the script performs a direct file overwrite of the agent's system prompt/instructions.
  • Capability inventory: The skill possesses bash execution and file-write (cp) capabilities.
  • Sanitization: No sanitization or validation of the content within the markdown files is performed before they are promoted to the primary instruction file.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 07:36 AM