semantic-scholar
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides an interface to retrieve academic paper metadata and abstracts from the Semantic Scholar API, creating a surface for indirect prompt injection.\n
- Ingestion points: Data ingestion occurs via the
relevanceSearch,paper,citations,references, andrecommendationstools described in SKILL.md.\n - Boundary markers: The instructions do not define delimiters or specific safety instructions to isolate the retrieved paper content from the agent's core instructions.\n
- Capability inventory: The skill includes tools for searching, batch lookups, and citation graph traversal, which process data that could influence the agent's subsequent logic.\n
- Sanitization: There is no evidence of content sanitization or validation for the data returned by the academic API.
Audit Metadata