htmx-expert

Pass

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to review and analyze user-provided code, which represents a standard ingestion surface for untrusted data.
  • Ingestion points: Analysis of target files specified via user input and the target property in schemas/input.schema.json.
  • Boundary markers: The skill instructions do not specify explicit delimiters or isolation instructions for the processed content.
  • Capability inventory: The skill is configured with Read, Write, Edit, and Bash tools in the metadata.
  • Sanitization: No explicit sanitization or filtering of external content is defined.
  • [SAFE]: The 'Memory Protocol' instruction in SKILL.md (reading .claude/context/memory/learnings.md) is a benign context management pattern used to maintain state across agent sessions. The provided Node.js scripts and hooks contain only standard boilerplate for validation and metrics recording.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 5, 2026, 08:16 PM