research
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where the agent ingests data from external sources, creating a potential vector for malicious instructions.
- Ingestion points: Instructions in SKILL.md tell the agent to research official docs, source code, and first-party APIs.
- Boundary markers: The skill lacks instructions to delimit or ignore potentially malicious content found in these sources.
- Capability inventory: The agent has the capability to write research findings into markdown files within the repository.
- Sanitization: There are no requirements for sanitizing or escaping the content retrieved from external sources before it is persisted to the file system.
Audit Metadata