participation-warmup-planner
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to process external, untrusted data including community rule pages, moderator statements, and screenshots. It includes a specific security section that instructs the agent to treat these inputs as untrusted and explicitly forbids external content from rewriting guardrails, declaring channels graduated, or authorizing promotions. This provides effective mitigation against indirect prompt injection.
- [COMMAND_EXECUTION]: The skill references local scripts (such as
registry-events.py,discourse.py, andhn.py) to retrieve community data and manage internal state transitions. These script calls are restricted to authorized internal operations and do not involve the execution of arbitrary shell commands or user-supplied code. - [DATA_EXFILTRATION]: No patterns of data exfiltration were detected. The skill's network operations are limited to reading from public community surfaces and its write operations are confined to designated internal project directories (
memory/social/,memory/events/). There is no evidence of sensitive data being transmitted to external or unauthorized servers.
Audit Metadata