llmdocs

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the codebase to generate documentation, which is a common surface for indirect prompt injection.
  • Ingestion points: Reads files, git diff output, and git log in the SKILL.md 'Gather Context' section.
  • Boundary markers: The skill does not define specific delimiters to separate codebase content from instructions.
  • Capability inventory: Includes file writing (CLAUDE.md, .llmdocs/) and standard git command execution.
  • Sanitization: No explicit sanitization or filtering of codebase content is performed before processing.
  • [COMMAND_EXECUTION]: The skill executes standard git commands (git log, git diff, git status) to analyze changes. This is standard behavior for a documentation-syncing tool and is restricted to the project's directory.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 06:30 PM
Security Audit — agent-trust-hub — llmdocs