bs-article-illustrate

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using npx for Mermaid diagram validation and rendering (npx -y @mermaid-js/mermaid-cli -i <file>.mmd -o <file>.svg).
  • [EXTERNAL_DOWNLOADS]: The skill utilizes npx to download and execute the @mermaid-js/mermaid-cli package from the npm registry. It also fetches article content from user-provided URLs during the pre-flight phase.
  • [PROMPT_INJECTION]: The skill processes untrusted content from external articles, which could contain instructions designed to manipulate the agent's behavior.
  • Ingestion points: Article text or URLs provided by the user in the Pre-Flight phase (SKILL.md).
  • Boundary markers: Absent; there are no explicit delimiters or instructions to ignore embedded commands within the processed articles.
  • Capability inventory: Shell command execution (npx), file system writes (scratch files and temporary diagram files), and network access (URL fetching).
  • Sanitization: None; the skill reads and interprets the full article content to identify signals for illustration.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 03:30 AM
Security Audit — agent-trust-hub — bs-article-illustrate