genshijin-stats
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process Claude Code session logs, which contain untrusted data from previous model turns and terminal outputs. This represents an attack surface for indirect prompt injection.
- Ingestion points: Claude Code session logs (referenced in SKILL.md).
- Boundary markers: The skill documentation does not specify the use of delimiters or 'ignore' instructions to isolate the log content from the agent's core instructions.
- Capability inventory: The skill utilizes JavaScript hooks to perform file read operations and formatted output generation.
- Sanitization: No sanitization, validation, or filtering mechanisms for the log content are described.
- [DYNAMIC_EXECUTION]: The skill's primary logic is offloaded to external JavaScript files (
hooks/genshijin-stats.jsandhooks/genshijin-mode-tracker.js) which are executed at runtime. These scripts reside locally but act as the functional engine for the skill's capabilities.
Audit Metadata