skill-idea-miner

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill reads session logs from ~/.claude/projects/, which contain sensitive history of user messages and tool interactions. Evidence: scripts/mine_session_logs.py iterates through and reads JSONL files in the user's local Claude projects directory.
  • [COMMAND_EXECUTION]: The skill uses subprocess.run to call the claude CLI for idea extraction and scoring. Evidence: scripts/mine_session_logs.py and scripts/score_ideas.py both execute the claude command with user-derived content as input.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it interpolates untrusted user messages from session logs into prompts for the Claude CLI. Ingestion points: scripts/mine_session_logs.py parses message content from .jsonl files. Boundary markers: The prompt structure uses JSON formatting but lacks explicit security delimiters for raw log content. Capability inventory: The skill can execute local commands (claude CLI) and write files to the system (raw_candidates.yaml, idea_backlog.yaml). Sanitization: Includes a filter for automated prompt prefixes (_is_automated_prompt) and uses structured JSON parsing (_extract_json_from_claude) for LLM output.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 11:35 AM