skills/karlorz/llm-wiki/wiki-add-task/Gen Agent Trust Hub

wiki-add-task

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill captures untrusted user input and stores it for later automated discovery by a dev-loop, creating an indirect prompt injection surface.
  • Ingestion points: User-provided text argument in Step 1.
  • Boundary markers: Uses YAML frontmatter and Markdown headings; lacks explicit escaping for data structure delimiters such as triple-dashes (---).
  • Capability inventory: Calls the skillwiki CLI and performs file writing and appending operations to the vault.
  • Sanitization: Includes a Sensitive content guard (Step 2) that redacts credentials and tokens, and uses slugification to sanitize filenames, though it does not explicitly escape markdown structural characters.
  • [COMMAND_EXECUTION]: The skill invokes the skillwiki CLI tool to resolve environment configurations including vault paths and language settings. This tool is a functional component of the vault environment and is used appropriately.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 11:30 AM
Security Audit — agent-trust-hub — wiki-add-task