install-rules

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches content from external, user-specified Git repositories.\n
  • Evidence: Behavior 1 in SKILL.md describes cloning or fetching rules from a Git owner/repo or full URL provided by the user.\n- [COMMAND_EXECUTION]: The skill performs persistent file system modifications by writing to IDE configuration paths.\n
  • Evidence: SKILL.md outlines writing .mdc files to ./.cursor/rules/ and modifying ./.trae/project_rules.md.\n- [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection by ingesting untrusted data and writing it to high-influence configuration files.\n
  • Ingestion points: Rules read from remote Git repositories (SKILL.md).\n
  • Boundary markers: None. The instructions mandate preserving the rule body exactly as provided in the source.\n
  • Capability inventory: File system write operations to .cursor/rules/ and .trae/project_rules.md which control agent behavior.\n
  • Sanitization: None. The content is preserved without filtering or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 11:36 PM