studio-source-control

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill documents standard ServiceNow source control procedures. No patterns of prompt injection, data exfiltration, or malicious command execution were found. All external references are related to standard ServiceNow table structures (e.g., sys_app, sys_repo_credential) and REST API endpoints (/api/sn_source_control).
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests data from external ServiceNow tables and repository metadata. However, this is an inherent and necessary function for the skill's purpose.
  • Ingestion points: Data retrieved from ServiceNow tables via snow_query_table and status/branch information from snow_source_control (SKILL.md).
  • Boundary markers: The skill does not define specific boundary markers for ingested data in the tool calls, but the data sourced (application metadata) is typically platform-controlled.
  • Capability inventory: Tools include the ability to perform write operations to Git repositories (commit, push, branch creation) and query instance tables.
  • Sanitization: No explicit sanitization or validation of the retrieved metadata is described within the instruction text, though the primary use case involves processing system records rather than untrusted user input.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 07:16 PM
Security Audit — agent-trust-hub — studio-source-control