skills/jeremylongshore/claude-code-plugins-plus-skills/salesforce-performance-tuning/Gen Agent Trust Hub
salesforce-performance-tuning
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates the processing of data from Salesforce objects into the agent's context, creating a potential surface for indirect prompt injection.
- Ingestion points: Data retrieved from Salesforce via queries described in
SKILL.md. - Boundary markers: The skill does not provide specific delimiters or instructions to treat data from Salesforce as untrusted.
- Capability inventory: The skill is granted
Read,Write, andEditpermissions, which could be leveraged if malicious instructions in the retrieved data are executed. - Sanitization: No explicit data sanitization or validation is included in the provided code snippets.
Audit Metadata