NYC
skills/johnlindquist/claude/article/Gen Agent Trust Hub

article

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • EXTERNAL_DOWNLOADS (LOW): The skill instructs the installation of @anthropic-ai/claude-cli via NPM and google-generativeai via Pip. Both packages originate from trusted organizations (Anthropic and Google), which downgrades the severity of these external dependencies per the trust-scope rule.
  • COMMAND_EXECUTION (LOW): The skill utilizes shell commands (claude, gemini) to perform its primary function of article generation. This is appropriate for its stated purpose.
  • PROMPT_INJECTION (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8) due to the way it handles external data.
  • Ingestion points: The skill reads external content from draft.md and accepts various user-provided placeholders like [topic], [task], and [feedback].
  • Boundary markers: No delimiters or "ignore embedded instructions" warnings are used when interpolating file content into prompts.
  • Capability inventory: The skill executes AI generation commands that could be influenced by malicious instructions embedded within the draft.md file.
  • Sanitization: There is no evidence of sanitization or escaping of the $ARTICLE variable before it is passed to the shell-based CLI commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:01 PM