The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes data from an external log file that can contain untrusted content, which is then formatted into a report for the AI.\n
Ingestion points: The scripts/analyze_skill_usage.py script reads the note field from the user-controlled 06 计划/skill_usage_log.jsonl file.\n
Boundary markers: Absent. The AI instructions for Step 2 do not include delimiters or instructions to ignore embedded commands within the log data.\n
Capability inventory: The skill has the capability to read local files, execute scripts, and generate text reports based on the processed data.\n
Sanitization: Absent. The script directly prints the content of the note field to the AI context without validation or escaping.\n- [COMMAND_EXECUTION]: The skill executes a local Python script scripts/analyze_skill_usage.py to perform the data analysis. While this is the intended functionality, it involves local process execution.

skill-analyzer