search-specialist
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and does not include any executable scripts, binary files, or network-active code.
- [PROMPT_INJECTION]: No evidence of direct prompt injection, jailbreak attempts, or instructions to bypass safety guidelines was found.
- [DATA_EXFILTRATION]: There are no hardcoded credentials, API keys, or instructions to access sensitive local files or exfiltrate data to external servers.
- [PROMPT_INJECTION]: Regarding indirect prompt injection (Category 8): The skill possesses an attack surface as it is designed to ingest and process untrusted content from the web. 1. Ingestion points: External web content and search results fetched during research (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Limited to information gathering and synthesis; no system-level command execution or file-writing capabilities are defined in the provided file. 4. Sanitization: The skill mandates fact-verification across multiple sources and tracking contradictions, which acts as a verification layer to mitigate unreliable or malicious content.
Audit Metadata