turkish-prompt-compiler
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a custom Node.js script (scripts/count_tokens.cjs) and instructs the agent to execute it via the shell. This script utilizes the
fsmodule to read local files provided through command-line arguments to calculate token and character statistics. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process substantial Turkish prompts for optimization and restructuring, which creates a vulnerability surface for instructions embedded within the processed text.
- Ingestion points: User-provided Turkish prompts intended for token analysis, compression, or restructuring as defined in SKILL.md.
- Boundary markers: None. The skill instructions do not mandate the use of delimiters or specific safety headers to isolate the untrusted input text from the agent's instructions.
- Capability inventory: The skill has the capability to execute shell commands and perform file system read operations using the included scripts.
- Sanitization: None. The provided script reads and processes file contents directly without validation of the input data.
Audit Metadata