khalas
Warn
Audited by Gen Agent Trust Hub on Jul 7, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the
khalasCLI tool. It interpolates user-provided text directly into the command arguments (e.g.,khalas optimize "[user_input]"). This pattern is vulnerable to shell command injection if the user input contains special characters like semicolons, backticks, or pipe symbols, which could allow an attacker to execute arbitrary commands on the underlying system. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection vulnerabilities due to the way it handles untrusted data.
- Ingestion points: User-supplied text strings enter the agent's context through the input parameters for the
khalastool commands inSKILL.md. - Boundary markers: Absent. There are no instructions to use delimiters or ignore embedded instructions within the processed text.
- Capability inventory: The skill enables shell command execution via the
khalasbinary to perform text analysis and optimization. - Sanitization: Absent. The instructions lack any requirement to escape shell metacharacters or validate the input text before it is executed.
Audit Metadata