tooluniverse-target-research

Warn

Audited by Snyk on Jul 30, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (medium risk: 0.30). The skill’s runtime uses the user-supplied “Target Query” to drive tool calls for identifier resolution and downstream lookups (e.g., path_0_open_targets takes ids['ensembl'] derived from the user query, and the literature path ultimately issues PubMed seed queries from ids['symbol']/synonyms derived from the query), so the agent ingests outsider-provided free text via the user’s query parameter at least for search-string construction and identifier resolution.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 30, 2026, 03:11 AM
Issues
1