research
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external sources such as official documentation, source code, and APIs, creating a surface for indirect prompt injection if those sources contain instructions intended to manipulate agent behavior.
- Ingestion points: Primary sources including official documentation, source code, and first-party APIs accessed during research (SKILL.md).
- Boundary markers: No specific delimiters or instructions are provided to the agent to distinguish external content from its primary directives.
- Capability inventory: The skill allows the agent to write Markdown files to the local repository.
- Sanitization: No explicit filtering or validation of external content is specified before it is processed or stored.
Audit Metadata