skills/openclaw/skills/claw-diary/Gen Agent Trust Hub

claw-diary

Warn

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • EXTERNAL_DOWNLOADS (MEDIUM): The skill triggers the global installation of the claw-diary package via NPM. The author 0xbeekeeper and the organization openclaw are not included in the trusted external sources list, making the dependency unverifiable.
  • COMMAND_EXECUTION (MEDIUM): The skill executes multiple shell commands using the claw-diary binary, including summarizing logs, searching history, and exporting data. While it attempts to handle arguments safely for the search command, the binary itself is from an untrusted source.
  • PROMPT_INJECTION (LOW): The /diary:thoughts command implements an indirect prompt injection surface (Category 8) by processing untrusted log data.
  • Ingestion points: Reads data from ~/.claw-diary/events/*.jsonl, ~/.claw-diary/persona.md, and historical journal files.
  • Boundary markers: Employs a natural language security note advising the agent to treat content as factual context and ignore embedded instructions.
  • Capability inventory: Executes the claw-diary CLI and has read/write access to the ~/.claw-diary/ directory.
  • Sanitization: Relies on instructional constraints rather than technical sanitization, schema validation, or robust delimiters for the ingested log content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 19, 2026, 12:37 PM