stacktree-publish

Pass

Audited by Gen Agent Trust Hub on Jul 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a local shell script, scripts/publish.sh, to handle the uploading of generated HTML artifacts. The script is implemented using safe argument passing techniques to prevent injection vulnerabilities.
  • [EXTERNAL_DOWNLOADS]: The skill interacts with the vendor's API at https://api.stacktr.ee via curl. This network activity is restricted to the skill's documented purpose of hosting web content and targets the developer's official domain.
  • [PROMPT_INJECTION]: The skill manages HTML content which may be derived from external sources, creating an indirect prompt injection surface.
  • Ingestion points: HTML artifacts are passed to the publish.sh script through standard input.
  • Boundary markers: The instructions guide the agent to wrap fragments in standard HTML structures (e.g., <!doctype html>).
  • Capability inventory: The skill uses curl to transmit data to the vendor's API.
  • Sanitization: The skill features a built-in PII scanner that defaults to 'block' mode. This scanner is designed to detect and stop the transmission of sensitive information such as API keys (e.g., sk-, AKIA), emails, and credit card numbers.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 3, 2026, 10:16 AM
Security Audit — agent-trust-hub — stacktree-publish