platform-datamask-run

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes record data from Salesforce DataMaskPolicyJobRun and DataMaskPolicyJobRunDtl objects to determine job status and results.
  • Ingestion points: The scripts/poll-job.sh script and various sf data query commands in SKILL.md.
  • Boundary markers: Absent; data is processed as returned by the CLI without special delimiters.
  • Capability inventory: Shell command execution via sf, REST API requests, and local file writing.
  • Sanitization: Absent; the skill extracts values directly for reporting purposes.
  • [DYNAMIC_EXECUTION]: The helper script scripts/poll-job.sh utilizes python3 -c for inline execution of Python code to parse JSON output from the Salesforce CLI.
  • Evidence: The script contains python3 -c 'import json,sys; r=json.load(sys.stdin).get("result",{}).get("records",[]); print(r[0]["Status"] if r else "UNKNOWN")'. This is a low-risk, standard implementation for basic data extraction.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 04:35 PM
Security Audit — agent-trust-hub — platform-datamask-run