scrivener-stats

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes local Python scripts located at ${CLAUDE_PLUGIN_ROOT}/tools/scrivener/cli.py to analyze Scrivener projects. These operations are read-only and specific to statistical reporting.
  • [SAFE]: File access is limited to reading data from local .scriv packages provided by the user. No network exfiltration, persistence, or credential harvesting patterns were detected.
  • [PROMPT_INJECTION]: An indirect prompt injection surface is present because the skill processes untrusted external data from project files. 1. Ingestion points: The skill reads content.rtf for manuscript text and writing.history for session logs. 2. Boundary markers: Absent. 3. Capability inventory: Execution of local CLI tools (stats, stats-history, stats-frequency) for data processing, with no network or file-write permissions. 4. Sanitization: Absent. The risk is categorized as low due to the read-only nature and narrow statistical scope of the tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 12:26 PM
Security Audit — agent-trust-hub — scrivener-stats