salesforce
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches and executes the @useclawlink/cli package from the NPM registry using npx. This is a vendor-owned resource providing the core functionality for the skill.
- [COMMAND_EXECUTION]: Employs shell commands to invoke the ClawLink CLI for Salesforce operations such as querying records, listing objects, and executing CRM actions.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from Salesforce records (SOQL/SOSL results), which could contain instructions intended to influence the agent's behavior.
- Ingestion points: External data enters the context via
salesforce_soql_query,salesforce_find_records,salesforce_sosl_search, and record retrieval actions. - Boundary markers: No explicit delimiters or instructions to ignore embedded content were found in the skill definitions.
- Capability inventory: The skill has the capability to execute shell commands via the ClawLink CLI and perform write actions in Salesforce.
- Sanitization: No evidence of filtering or sanitization of record content prior to processing was identified.
Audit Metadata