homepage-audit
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes content from external, untrusted sources without implementing security delimiters or instructions.
- Ingestion points: User-provided URLs or pasted text are processed using the
web_fetchtool inSKILL.mdandSKILL-OC.md. - Boundary markers: Absent. There are no clear markers or instructions to the agent to ignore commands within the fetched content.
- Capability inventory: The skill uses
web_fetchto retrieve content from the internet. - Sanitization: Absent. No sanitization or validation logic is specified for the external data.
Audit Metadata