researchers-tech
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it is designed to ingest and process untrusted data from external sources such as tech blogs, mailing lists, and web searches.\n
- Ingestion points: External content retrieved via
WebFetchandWebSearchtools, as well as data from Git logs and public repositories.\n - Boundary markers: The instructions do not specify the use of delimiters or clear separation between retrieved data and system instructions.\n
- Capability inventory: The skill is granted
Write,Edit, andReadpermissions on the local file system, allowing it to document findings into files.\n - Sanitization: There are no explicit instructions for sanitizing, filtering, or validating the content retrieved from external sources before it is processed or written to disk.\n- [SAFE]: No malicious patterns, such as credential exfiltration, prompt injection, or obfuscation, were detected. The skill uses official and well-known technology resources (e.g., kernel.org, debian.org, arstechnica.com) for its research tasks.
Audit Metadata