The Agent Skills Directory

[SAFE]: The skill is scoped exclusively to read-only performance analysis and explicitly prohibits the use of mutating tools or logging raw response data.
[SAFE]: No obfuscation, unauthorized remote code execution, credential exposure, or persistence mechanisms were detected.
[SAFE]: The skill ingests external data via analytics tools, which constitutes an indirect prompt injection surface. However, the risk is negligible because the skill lacks destructive capabilities or network exfiltration tools.
Ingestion points: get_summary, get_top_posts, and get_follower_history tools referenced in SKILL.md.
Boundary markers: The instructions do not specify delimiters for external content.
Capability inventory: The skill environment is limited to read operations; it contains no file-system write access, shell execution, or external network transmission capabilities.
Sanitization: No explicit sanitization or filtering of external input is defined.

syndly-performance