skills/karlorz/llm-wiki/wiki-init/Gen Agent Trust Hub

wiki-init

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes a CLI utility named skillwiki with subcommands like path and init. These commands are used to determine target directories and perform the actual initialization of the vault.
  • [CREDENTIALS_UNSAFE]: The skill accesses and modifies ~/.skillwiki/.env. While .env files are identified as sensitive file paths, this specific file appears to be a vendor-owned configuration file used for binding vault settings, which is a standard practice for development tools.
  • [PROMPT_INJECTION]: The skill processes untrusted user input for the "domain question" and "taxonomy" and interpolates these values into shell command arguments (--domain "<answer>"). This creates an indirect prompt injection surface; however, this is inherent to the skill's primary function of processing user-defined parameters for project setup.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 11:30 AM
Security Audit — agent-trust-hub — wiki-init