The Agent Skills Directory

[COMMAND_EXECUTION]: The workflow section '1. Parse Input Parameters' instructs the agent to execute shell commands (ls -d <STORY_NAME>/ and ls <STORY_NAME>/chapters/...) using a variable <STORY_NAME> derived directly from user input. This pattern is vulnerable to command injection if the user provides a malicious string containing shell metacharacters (e.g., semicolons, backticks, or command substitution sequences) which the agent might execute without prior validation.
[DATA_EXFILTRATION]: Although no direct exfiltration commands are hardcoded, the identified command injection vulnerability could be exploited to run arbitrary shell commands that exfiltrate sensitive system information, environment variables, or local files to an external server.

pdf2audio-parallel