doc-chg-autopilot

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a local framework script located at ${CLAUDE_PLUGIN_ROOT}/tools/saga_driver.py using the Bash tool. This script acts as the primary orchestrator for the 'team' review mode.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it ingests and processes untrusted external data to generate change management records.
  • Ingestion points: Target artifacts, git diffs, incident references, and free-text change descriptions defined in the 'Input Contract' and 'Workflow' sections.
  • Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' warnings for the data being processed.
  • Capability inventory: The skill has the capability to execute shell commands via the Bash tool and perform file system write operations to update change registries (e.g., CHG-00_index.md).
  • Sanitization: Absent. There is no mention of sanitizing or escaping the content of the analyzed artifacts before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 08:55 PM
Security Audit — agent-trust-hub — doc-chg-autopilot