skills/inkeep/team-skills/nest-claude/Gen Agent Trust Hub

nest-claude

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Describes a method to bypass the claude CLI's built-in restriction on recursive nesting by unsetting specific environment variables (CLAUDECODE and CLAUDE_CODE_ENTRYPOINT).
  • [COMMAND_EXECUTION]: Provides instructions for using the --dangerously-skip-permissions flag, which allows child processes to execute all available tools (including file system and shell access) without human intervention or approval.
  • [COMMAND_EXECUTION]: Recommends the use of dynamically generated shell scripts (Pattern B) to manage the execution and synchronization of multiple background processes.
  • [PROMPT_INJECTION]: Establishes a surface for indirect prompt injection through the following mechanisms:
  • Ingestion points: Untrusted data can enter the agent context via the child's prompt flag (-p) or file-reading tools within the SKILL.md workflows.
  • Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are provided in the recommended prompt templates or file-based IPC examples.
  • Capability inventory: Full access to host system tools (Bash, Read, Write) is granted to the child processes via the auto-approval flag, allowing actions to be taken based on injected content.
  • Sanitization: No input validation or escaping logic is suggested for the data being passed into nested instances or written to shared state files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 08:31 PM