trump-perspective

Fail

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: CRITICALEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The research documentation in references/research/03-expression-dna.md contains a URL (https://ijels.com/upload_document/issue_files/70IJELS-1042024-TheArt.pdf) that automated scanners have flagged as a malicious Botnet link. Furthermore, the file references/research/03-expression-dna.md is identified as infected (MD:HttpRequest-inf) and malicious (FileRepMalware).
  • [INDIRECT_PROMPT_INJECTION]: The skill relies on extensive external research data (approximately 320KB) derived from automated web searches. This data is ingested into the agent's context and includes untrusted links and content from third-party sources, including the confirmed malicious URL. 1. Ingestion points: All markdown files within the references/research/ directory. 2. Boundary markers: The skill instructions lack explicit delimiters or warnings to ignore embedded instructions within these large research files. 3. Capability inventory: The agent is granted WebSearch capabilities and is specifically instructed in SKILL.md to analyze the behavior and logic found in these research files. 4. Sanitization: There is no evidence of validation or filtering for the external URLs or content contained in the research files.
Recommendations
  • CRITICAL: 1 infected file(s) detected - DO NOT USE
  • CRITICAL: 1 file(s) identified as malware by FileRep - DO NOT USE
  • AI detected serious security threats
  • Contains 2 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Aug 27, 2026, 03:04 AM
Security Audit — agent-trust-hub — trump-perspective