openclaw-session-cleaner
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to perform file system operations within the
~/.openclaw/agents/main/sessions/directory, including file counting, bulk deletion of.jsonlfiles, and modification of thesessions.jsonindex. - [INDIRECT_PROMPT_INJECTION]: The skill processes session data which may contain untrusted input from previous interactions. Reading these files during the cleanup or rebuilding phase presents a surface for indirect prompt injection attacks.
Audit Metadata