init-claude-md

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands like ls, cat, and grep to inspect project files such as package.json, README.md, and dependency manifests. These are standard operations for a build/init tool to identify stack and commands.
  • [PROMPT_INJECTION]: The skill processes content from untrusted local files (e.g., README.md), creating a surface for indirect prompt injection where malicious instructions in project files could influence agent behavior.
  • Ingestion points: Reads local project files including package.json, README.md, Cargo.toml, requirements.txt, go.mod, and Makefile in SKILL.md.
  • Boundary markers: No explicit delimiters or boundary markers are used when reading external file content.
  • Capability inventory: Shell command execution (ls, cat, grep) and file writing (Write a CLAUDE.md).
  • Sanitization: The skill does not perform sanitization or filtering of the content read from files before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 08:48 AM
Security Audit — agent-trust-hub — init-claude-md