process-mining-insights

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions and metadata do not contain any malicious patterns such as prompt injection, obfuscation, or unauthorized exfiltration. All functionalities are consistent with the stated purpose of business process analysis.
  • [COMMAND_EXECUTION]: The skill lists Bash as a native tool and provides examples for using it to perform REST API queries against ServiceNow. This is a legitimate requirement for retrieving process data.
  • [DATA_EXFILTRATION]: Network operations are directed exclusively at official ServiceNow API endpoints (/api/now/table/*). There is no evidence of data being sent to untrusted external domains.
  • [PROMPT_INJECTION]: This skill possesses an indirect prompt injection surface. 1. Ingestion points: Data is retrieved from ServiceNow tables such as sn_process_mining_process and sn_process_mining_case. 2. Boundary markers: No explicit delimiters are used for the ingested data. 3. Capability inventory: The skill has permission to use SN-Update-Record, SN-Add-Work-Notes, and Bash. 4. Sanitization: No sanitization or validation of the retrieved table data is documented. This surface is considered safe as it is inherent to the skill's primary analytical function.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 02:24 PM
Security Audit — agent-trust-hub — process-mining-insights