ai-visibility-fix-plan

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The README.md file contains installation instructions directing users to run npx skills add unifapi-agent/agents. This process downloads and executes packages from the developer's official repository.
  • [COMMAND_EXECUTION]: The skill documentation includes shell commands and plugin installation directives (npx, /plugin) intended for setting up the environment. These commands are tied to the vendor's infrastructure and the skill's stated purpose.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it utilizes tools like browser/markdown and geo/serp to retrieve and process content from external, third-party websites.
  • Ingestion points: External website content via browser/markdown and search engine results via geo/serp (defined in SKILL.md).
  • Boundary markers: The instructions do not specify explicit delimiters or 'ignore' instructions for the processed external data.
  • Capability inventory: No dangerous capabilities (such as file system writes, subprocess execution, or arbitrary network requests) are present in the skill's instructions.
  • Sanitization: There are no explicit sanitization or filtering steps defined for the ingested data, though the skill's output is limited to a structured report.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 10:28 AM
Security Audit — agent-trust-hub — ai-visibility-fix-plan