pp-salesloft
Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads its core CLI tool and MCP server from the author's verified repositories, including the '@mvanhorn/printing-press-library' NPM package and the 'github.com/mvanhorn/printing-press-library' Go module.
- [DATA_EXFILTRATION]: The CLI tool supports a '--deliver webhook:' flag, which enables the agent to transmit Salesloft data (such as account details or activity logs) to any user-provided URL. This capability presents a surface for data exfiltration if the agent is manipulated into targeting malicious endpoints.
- [COMMAND_EXECUTION]: The skill executes the 'salesloft-pp-cli' binary to perform read operations on Salesloft API resources.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted data from the Salesloft API. 1. Ingestion points: CRM data such as person records, notes, and activity logs retrieved via CLI commands. 2. Boundary markers: No delimiters or specific instructions to ignore embedded commands are used when processing API output. 3. Capability inventory: Command execution via shell and external data transmission via webhooks. 4. Sanitization: No sanitization or filtering is applied to the API data before it is presented to the agent.
Audit Metadata