update-opportunity
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security concerns were identified. The skill targets standard Salesforce API endpoints and follows a secure workflow.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from Salesforce (external ingestion in SKILL.md) and has the capability to write back to the system. However, the risk is mitigated by a mandatory human-in-the-loop confirmation step ('Apply these changes? yes / edit / cancel') which prevents the agent from autonomously acting on potentially malicious instructions embedded in record fields. The skill also enforces the use of grounded field names and verification of changes post-execution.
Audit Metadata