skills/cexll/myclaude/codeagent/Gen Agent Trust Hub

codeagent

Warn

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates the execution of codeagent-wrapper, a tool designed to perform arbitrary code analysis and refactoring tasks. This includes capabilities for parallel execution and session management.
  • [COMMAND_EXECUTION]: Provides functionality to explicitly bypass security prompts using the --dangerously-skip-permissions flag or the CODEAGENT_SKIP_PERMISSIONS environment variable, which reduces user oversight during automated task execution.
  • [PROMPT_INJECTION]: Vulnerable to indirect prompt injection (Category 8) due to the processing of untrusted external content.
  • Ingestion points: Untrusted data enters the context via the task content and file references using the @file syntax (documented in SKILL.md).
  • Boundary markers: The skill uses HEREDOC (EOF) delimiters for command construction, but lacks explicit instruction boundary markers or warnings to the AI backend to ignore embedded commands within the ingested files.
  • Capability inventory: The skill allows for complex subprocess execution, file system interaction, and multi-file refactoring through the codeagent-wrapper command.
  • Sanitization: There is no evidence of sanitization, validation, or escaping of the content retrieved from @file references before it is passed to the AI backends.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 9, 2026, 06:26 AM