skills/rheinmir/setup/extract-site/Gen Agent Trust Hub

extract-site

Pass

Audited by Gen Agent Trust Hub on Jun 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill's primary function is to ingest and process untrusted content from external URLs. This creates a surface for indirect prompt injection, where an attacker could place malicious instructions inside a website's CSS comments, metadata, or hidden HTML elements to manipulate the agent's behavior or file output during the extraction process.
  • Ingestion points: Website content extracted from user-provided URLs in SKILL.md (Workflow Step 1).
  • Boundary markers: No specific delimiters or safety warnings are used to isolate extracted site data from the agent's instructions.
  • Capability inventory: The skill performs file system writes to the themes/ directory and the llmwiki/ repository.
  • Sanitization: No sanitization or validation of the ingested external content is mentioned before it is used to generate markdown and HTML files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 3, 2026, 04:49 AM
Security Audit — agent-trust-hub — extract-site