raycast-extensions
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION] (LOW): Indirect Prompt Injection Surface. The skill provides code examples that demonstrate ingesting untrusted data from external sources and processing it through an LLM without proper security boundaries.
- Ingestion points:
examples.md(viaClipboard.readText()),references/api/browser-extension.md(viaBrowserExtension.getContent()). - Boundary markers: Absent. Code examples interpolate external data directly into the prompt string (e.g.,
AI.ask(Summarize this: ${text})) without the use of XML tags, triple quotes, or specific instructions to ignore embedded commands. - Capability inventory: The skill utilizes
AI.askfor content processing andClipboard.copy,Clipboard.paste, andBrowserExtension.getContentfor data handling. - Sanitization: Absent. There is no evidence of input validation, character escaping, or content filtering before the data is passed to the AI model.
Audit Metadata