homepage-audit
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from external websites, which presents a surface for indirect prompt injection.
- Ingestion points: SKILL.md and SKILL-OC.md specify the use of web_fetch to retrieve content from user-provided URLs, as well as accepting copy-pasted text.
- Boundary markers: The instructions do not define delimiters or specific warnings to the agent to disregard instructions found within the fetched content.
- Capability inventory: The skill's functionality is limited to performing audits, scoring, and generating text; no file-system access, remote code execution, or network exfiltration capabilities were observed.
- Sanitization: No sanitization or filtering mechanisms are described for the data retrieved from external sources.
Audit Metadata