skills/freedomintelligence/openclaw-medical-skills/tooluniverse-chemical-compound-retrieval/Gen Agent Trust Hub
tooluniverse-chemical-compound-retrieval
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill uses established scientific APIs for chemical property and bioactivity retrieval. There is no evidence of unauthorized data access or exfiltration to untrusted domains.\n- [SAFE]: All tool calls are performed through a structured framework (ToolUniverse) as part of the intended functionality. No secondary persistence or privilege escalation mechanisms are present.\n- [PROMPT_INJECTION]: The skill ingests untrusted user input (compound names, SMILES, InChI) and retrieves external data from PubChem/ChEMBL. While this constitutes an indirect prompt injection surface, it is considered safe as the data is used solely for generating a structured report and the skill environment lacks dangerous execution capabilities.
Audit Metadata