research
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted data from external research sources and has the capability to write to local files.
- Ingestion points: Content retrieved from external websites and databases via HTTP network operations (SKILL.md).
- Boundary markers: No explicit delimiters or boundary markers are used to isolate external content from the agent's core instructions (SKILL.md).
- Capability inventory: The skill has file:write permissions to the local research/ folder (SKILL.md).
- Sanitization: No sanitization, validation, or content filtering protocols are defined for the incoming data before processing (SKILL.md).
- [NO_CODE]: The skill contains no executable scripts, binaries, or configuration files and relies entirely on natural language instructions for the agent.
Audit Metadata