optimization-advisor
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious prompt injection patterns detected. The instructions follow a standard role-play structure for an analytical advisor.
- [SAFE]: Data ingestion is limited to reading a specific context file (
.agents/social-media-context.md) and using platform-provided tools (list_posts,get_post_analytics, etc.). This aligns with the skill's primary purpose. - [SAFE]: No evidence of data exfiltration, obfuscation, or remote code execution. The skill does not perform network requests to external third-party domains or execute untrusted scripts.
- [SAFE]: Indirect Prompt Injection Surface: The skill processes external data (social media post content). While it lacks boundary markers (Cat 8), it also lacks high-risk capabilities like command execution or file-writing, mitigating potential impact. Ingestion of this data is necessary for its primary function.
Audit Metadata