skills/openclaw/skills/homepage-audit/Gen Agent Trust Hub

homepage-audit

Pass

Audited by Gen Agent Trust Hub on Feb 23, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill consists entirely of natural language instructions and markdown checklists. It does not include any scripts, executables, or package dependency files.
  • [PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external websites, which presents a surface for indirect prompt injection.
  • Ingestion points: The skill instructs the agent to fetch URLs or analyze screenshots and text provided by users in the 'Audit Without Access' section (SKILL.md).
  • Boundary markers: The instructions do not define specific delimiters or include warnings for the agent to ignore instructions embedded within the content of the audited pages.
  • Capability inventory: The skill itself has no code, but it is intended for use with an agent's web-fetching and vision capabilities.
  • Sanitization: No sanitization or filtering of the external website content is described in the prompt logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 23, 2026, 08:46 AM