platform-datamask-run
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input, such as job IDs and policy IDs, and interpolates them directly into shell commands and REST API paths.
- Ingestion points: User-provided or query-retrieved
jobRunId,policyId, andobjectIdvalues. - Boundary markers: None identified. Inputs are directly interpolated into command strings.
- Capability inventory: The skill has the capability to query, create, update, and delete records, deploy metadata, and make REST API requests to the Salesforce environment.
- Sanitization: No explicit sanitization or validation of the input variables is described before they are used in shell executions.
- [DYNAMIC_EXECUTION]: The skill utilizes a local helper script that executes Python code via a command-line string to parse JSON output from tool calls.
- Evidence: The script
scripts/poll-job.shcontains the commandpython3 -c "import json,sys; r=json.load(sys.stdin).get('result',{}).get('records',[]); print(r[0]['Status'] if r else 'UNKNOWN')"to extract status information from the Salesforce CLI response.
Audit Metadata