paper-search
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs authorized network communications with official academic services and government portals (kci.go.kr, data.go.kr, riss.kr) and manages API keys using standard local storage practices in environment files.
- [PROMPT_INJECTION]: The skill possesses a theoretical attack surface for indirect prompt injection as it processes and summarizes untrusted academic content from external sources.
- Ingestion points: Paper titles and abstracts retrieved from third-party academic databases specified in SKILL.md.
- Boundary markers: The skill does not define specific delimiters to separate ingested content from the agent's internal instructions.
- Capability inventory: File system write access for storing credentials and network capabilities via WebSearch and WebFetch tools.
- Sanitization: No explicit sanitization or validation of the retrieved scholarly data is documented.
Audit Metadata