narrative-review
Pass
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of processing large quantities of external data.
- Ingestion points: The skill targets a high volume of external data, including 80 web search results, 15 web research pages, and 50 academic paper overviews (SKILL.md).
- Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external content as untrusted or to ignore instructions embedded within the source materials.
- Capability inventory: The skill utilizes integrated search and research subagents to synthesize findings. If these processes are influenced by malicious data, the final synthesis could be manipulated to include attacker-specified content or bias.
- Sanitization: The instructions do not define any sanitization, filtering, or validation steps for the data retrieved from the internet or academic databases before processing.
Audit Metadata