skills/illyism/seo-skills/unslop-seo/Gen Agent Trust Hub

unslop-seo

Warn

Audited by Gen Agent Trust Hub on Nov 12, 2026

Risk Level: MEDIUMDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [DYNAMIC_EXECUTION]: The skill executes a Python script using a shell heredoc to validate file content against SEO rules. Executing code provided within instructions is a dynamic execution pattern.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted text from project files (MDX, HTML, TSX) and performs in-place edits. It lacks boundary markers to separate data from instructions and does not sanitize input, potentially allowing embedded malicious instructions in the edited files to influence the agent. 1. Ingestion points: local repository files. 2. Boundary markers: Absent. 3. Capability inventory: file read and write. 4. Sanitization: None.
  • [COMMAND_EXECUTION]: The skill executes git diff to identify files to be processed when user input is missing.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 12, 2026, 03:54 AM