3d-cartoon-character-short
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to access external content from goodcase.ai using browser or media inspection tools. This involves network requests to a third-party domain not included in the standard whitelist.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external websites, which creates a vulnerability to indirect prompt injection if the source content contains malicious instructions.
- Ingestion points: External URLs for case evidence and media located in
references/cases.md. - Boundary markers: None; there are no instructions provided to treat the external data as untrusted or to ignore potential commands within it.
- Capability inventory: The agent is empowered to use browsing and media tools to analyze the external content.
- Sanitization: The skill lacks a sanitization step to filter instructions or unsafe patterns from the external data before it is incorporated into the prompt generation process.
Audit Metadata