web-quality-audit
Pass
Audited by Gen Agent Trust Hub on Jul 10, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from external sources and has the capability to perform actions based on that data.\n
- Ingestion points: The skill ingests untrusted data from URLs, page source, screenshots, and repositories as defined in SKILL_CARD.md.\n
- Boundary markers: The instructions lack explicit boundary markers or directives to isolate external content from system directives.\n
- Capability inventory: The skill is authorized to modify local code files to fix issues and execute browser-based tools for auditing.\n
- Sanitization: There is no documented procedure for sanitizing or validating ingested content before it is processed or used to inform actions.
Audit Metadata