ai-automation-workflows
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute specific Python scripts located in the local file system to perform automation tasks.
- Evidence: Execution of
~/.openclaw/scripts/inference_flow_run.py,~/.openclaw/scripts/handoff-to-paperclip.py, and~/.openclaw/scripts/test-distribution-flow.py. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data packets that could influence agent behavior.
- Ingestion points: The skill reads external JSON data from file paths provided to the
--packetargument. - Boundary markers: There are no explicit instructions or delimiters defined to isolate or ignore instructions that might be embedded within the packet data.
- Capability inventory: The agent has the capability to execute shell commands (
python3) and interact with downstream systems like 'Paperclip'. - Sanitization: No sanitization or validation of the packet content is mentioned before it is passed to the execution scripts.
Audit Metadata