research
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external, untrusted sources which exposes an attack surface for indirect instructions.
- Ingestion points: The instructions in
SKILL.mddirect the agent to fetch data from "primary sources" including official documentation, source code, specifications, and first-party APIs. - Boundary markers: There are no explicit instructions or delimiters defined to ensure the agent ignores potentially malicious natural language instructions embedded within the research material.
- Capability inventory: The skill possesses the capability to write findings into Markdown files within the local repository environment.
- Sanitization: The skill lacks specified mechanisms for sanitizing, escaping, or validating the content retrieved from external sources before it is committed to the file system.
Audit Metadata