apple-docs-research
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [Prompt Injection] (SAFE): The skill contains no attempts to override agent instructions or bypass safety guidelines. Instructions are focused on documentation lookup workflows.
- [Data Exposure & Exfiltration] (SAFE): No sensitive file paths, hardcoded credentials, or unauthorized network operations were detected.
- [Indirect Prompt Injection] (LOW):
- Ingestion points: The skill retrieves external content from Apple Developer Documentation and WWDC session data via MCP tools like
get_apple_doc_contentandsearch_wwdc_content. - Boundary markers: None explicitly defined in the instruction set.
- Capability inventory: The skill is restricted to information synthesis and display; it lacks capabilities for file modification, command execution, or external network writes.
- Sanitization: Not explicitly implemented, but the low-privilege nature of the skill mitigates the risk of processing untrusted external content.
- [External Downloads & RCE] (SAFE): The skill does not reference external packages (Python/Node.js) or attempt to execute remote scripts.
- [Obfuscation] (SAFE): No Base64, zero-width characters, or homoglyphs were identified. The text is clear and readable.
Audit Metadata