skills/syf2211/ruledoctor/ruledoctor/Gen Agent Trust Hub

ruledoctor

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill functions by reading instructions from external rule and configuration files, which presents a surface for indirect prompt injection.
  • Ingestion points: Project rule files (e.g., CLAUDE.md, .cursorrules, .cursor/rules/*.md) and the .ruledoctor.json configuration file (SKILL.md).
  • Boundary markers: Absent; the skill does not instruct the agent to use delimiters or ignore potentially malicious instructions embedded within the ingested rule content.
  • Capability inventory: The agent can read files and is instructed to conditionally refuse command executions (e.g., git push --force) based on rule content.
  • Sanitization: Absent; rule file content is not validated or escaped before being processed by the agent.
  • [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute specific shell commands using a vendor-provided CLI tool.
  • Evidence: The command ruledoctor --cwd "<项目根>" --last-session is specified for reporting, and ruledoctor setup is mentioned for installing command-interception hooks (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 02:41 AM
Security Audit — agent-trust-hub — ruledoctor