research
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external, potentially untrusted data from primary sources such as official documentation, source code, and APIs.
- Ingestion points: The background agent processes content from external documentation, source code repositories, and APIs (SKILL.md).
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are provided for the background agent to distinguish between data and instructions.
- Capability inventory: The agent has the ability to write findings as Markdown files to the local repository (SKILL.md).
- Sanitization: No explicit sanitization, validation, or filtering of the retrieved content is mentioned before it is processed and written back to the repository.
Audit Metadata