research
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external primary sources (documentation, source code, APIs) and writes to the local repository, which provides a surface for indirect prompt injection attacks.
- Ingestion points: External websites and files accessed during research tasks (SKILL.md).
- Boundary markers: The skill does not provide instructions to delimit or ignore embedded commands in the sources.
- Capability inventory: The skill is authorized to create and modify Markdown files in the repository (SKILL.md).
- Sanitization: There are no requirements for validating or sanitizing retrieved content before writing to the filesystem.
- [NO_CODE]: The skill consists of instructions and configuration metadata only, containing no scripts or executable code.
Audit Metadata