research
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data and has file-writing capabilities, which introduces a risk of indirect prompt injection.\n
- Ingestion points: The agent is instructed to investigate primary sources such as documentation and APIs in
SKILL.md.\n - Boundary markers: Absent; the skill does not use delimiters to isolate researched content from the agent's instructions.\n
- Capability inventory: The agent has the capability to write research findings into Markdown files in the repository (
SKILL.md).\n - Sanitization: Absent; there are no instructions to sanitize or escape the data retrieved from external sources before saving it.
Audit Metadata