cancer-discovery
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill content is restricted to legitimate academic advisory information. No malicious code, obfuscation, or unauthorized network activities were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest manuscript data and perform web searches, creating a surface for potential indirect prompt injection.
- Ingestion points: Manuscript details and content provided by the user.
- Boundary markers: Absent.
- Capability inventory: The skill prompts the agent to perform external web searches for updated journal guidelines.
- Sanitization: Absent.
Audit Metadata