rlm-cleanup-agent
Pass
Audited by Gen Agent Trust Hub on Apr 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute local Python scripts including cleanup_cache.py and inventory.py to manage the RLM ledger. This is consistent with its stated purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it processes external ledger data and possesses command-execution capabilities.
- Ingestion points: The agent reads RLM Summary Ledger files (*_cache.json) during cleanup and inventory tasks.
- Boundary markers: No delimiters or isolation instructions are provided to distinguish processed data from agent commands.
- Capability inventory: The agent has access to Bash, Read, and Write tools for script execution and ledger modification.
- Sanitization: No explicit validation or sanitization of the ledger contents is mentioned in the skill instructions.
Audit Metadata