god-consensus

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION] (LOW): The skill instructs the agent to execute several local shell scripts (e.g., council.sh, awakener.sh) using arguments provided by users or other agents. Direct interpolation of variables like DESCRIPTION and COMMENT into shell commands creates a command injection surface if the underlying scripts do not implement strict escaping.\n- [PROMPT_INJECTION] (LOW): The skill is susceptible to indirect prompt injection via the decision-making data it processes.\n
  • Ingestion points: Arguments passed to council.sh and the content of .god/council/decisions/DECISION_ID.json.\n
  • Boundary markers: Absent (no delimiters or 'ignore' instructions are used for the interpolated data).\n
  • Capability inventory: Invocation of shell scripts, system state observation, and file modification via jq.\n
  • Sanitization: Absent (the documentation does not specify sanitization or validation of the input strings before they are processed by the shell or the agent).
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:36 PM