exa
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- General Security (SAFE): No malicious patterns, hardcoded secrets, or obfuscated code were detected in the skill's instructions or metadata.
- Category 8: Indirect Prompt Injection (SAFE): The skill retrieves external web content but lacks high-risk capabilities that could be exploited via malicious data ingestion. 1. Ingestion points: External search results retrieved via the Exa AI semantic search query. 2. Boundary markers: No delimiters or specific boundary instructions are provided in the skill logic. 3. Capability inventory: No file-system access, dynamic code execution (eval/exec), or unauthorized network operations are present in the skill definition. 4. Sanitization: No specific sanitization logic is implemented in the provided markdown.
Audit Metadata