ai-deep-research
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a Python script
scripts/citation_verifier.pyintended for local execution by the user to verify research claims against a source ledger. The script uses standard libraries and performs benign text processing tasks. - [EXTERNAL_DOWNLOADS]: The skill references several well-known and trusted technology services and organizations, including OpenAI, Google DeepMind, Anthropic, xAI, and Perplexity for their official deep research API documentation and tools. These references are informative and align with the skill's primary purpose.
- [INDIRECT_PROMPT_INJECTION]: While the skill's primary function is to process external web data (creating an attack surface for indirect prompt injection), it explicitly addresses this risk through architectural patterns such as 'Verifier Isolation' (P4) and 'Hostile Source Detection' (P9), which are designed to mitigate the impact of malicious content embedded in research sources.
- [SAFE]: No malicious obfuscation, credential exfiltration, persistence mechanisms, or privilege escalation attempts were found. The skill follows best practices for AI agent development by emphasizing provenance, verification, and structured workflows.
Audit Metadata