art-history
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized access attempts were detected in the skill instructions. The primary functionality is to provide scholarly advice for manuscript submission.\n- [INDIRECT_PROMPT_INJECTION]: The skill instructions provide a potential surface for indirect prompt injection by requesting the agent to search for and ingest live journal guidelines.\n
- Ingestion points: External web search results for 'Art History journal author guidelines' from the Association for Art History or Wiley publisher sites.\n
- Boundary markers: None present in the instructions.\n
- Capability inventory: No executable scripts, subprocess calls, file-writing, or network exfiltration capabilities are defined within the skill itself.\n
- Sanitization: No explicit sanitization or filtering instructions are provided for the retrieved external data. This surface is evaluated as safe given the trusted nature of the academic publisher targets and the alignment with the skill's intended purpose.
Audit Metadata