session-logs

Pass

Audited by Gen Agent Trust Hub on Apr 18, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes bash loops and shell pipes involving utilities such as jq, rg (ripgrep), awk, and head/tail to process local log files.
  • [SAFE]: Accessing session transcripts in ~/.openclaw/agents/ is the primary and intended purpose of the skill, enabling the agent to retrieve historical context.
  • [SAFE]: The skill processes historical conversation data, which presents a surface for indirect prompt injection if prior messages contain instructions. 1. Ingestion points: Session logs stored in ~/.openclaw/agents//sessions/ (SKILL.md). 2. Boundary markers: Absent; text is extracted and displayed directly to the agent context. 3. Capability inventory: Shell execution (jq, rg, awk, bash). 4. Sanitization: Absent; the skill retrieves and displays raw message content.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 18, 2026, 12:42 PM