research
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and research information from external primary sources such as official documentation, source code, and APIs. This creates a surface for indirect prompt injection where malicious instructions embedded in the researched content could potentially influence the agent's behavior.
- Ingestion points: External primary sources, official documentation, source code, and first-party APIs mentioned in
SKILL.md. - Boundary markers: Absent. The instructions do not specify the use of delimiters or provide warnings to ignore embedded directives within the ingested content.
- Capability inventory: The agent is authorized to write research findings to a Markdown file within the repository filesystem.
- Sanitization: Absent. There is no mention of sanitizing or validating the external content before it is processed or written to the file.
Audit Metadata