skills/cacr92/wereply/codeagent/Gen Agent Trust Hub

codeagent

Warn

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes the codeagent-wrapper CLI tool, which is designed to perform deep code analysis, generation, and refactoring on the local file system.\n- [COMMAND_EXECUTION]: Provides an explicit mechanism to disable security permission prompts for the Claude backend via the --dangerously-skip-permissions flag or the CODEAGENT_SKIP_PERMISSIONS environment variable, which could allow unauthorized file modifications if the agent is compromised.\n- [PROMPT_INJECTION]: The skill exhibits surface area for indirect prompt injection (Category 8).\n
  • Ingestion points: Processes user-provided task descriptions and local file content referenced using the @ syntax, as seen in SKILL.md.\n
  • Boundary markers: Utilizes HEREDOC (<<'EOF') for task input but lacks explicit instructions or markers to prevent the agent from following instructions embedded within the ingested data or files.\n
  • Capability inventory: The codeagent-wrapper tool possesses high-privilege capabilities including file system writes, code refactoring, and parallel task execution.\n
  • Sanitization: There is no evidence of input validation, sanitization, or escaping of the task content or referenced file data before it is passed to the AI backends.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 12:26 AM