social-media-content-calendar
Pass
Audited by Gen Agent Trust Hub on Aug 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious code, persistence mechanisms, obfuscation, or unauthorized data exfiltration patterns were detected. The skill's primary functions are limited to content generation and planning within a social media context.- [PROMPT_INJECTION]: The skill was evaluated for its susceptibility to indirect prompt injection due to its data ingestion capabilities.\n
- Ingestion points: The skill collects external data using
read_fileandweb_extract(SKILL.md, Step 2).\n - Boundary markers: Not explicitly defined for data interpolation.\n
- Capability inventory: Capabilities include file and web reading, image generation, and publishing via the
xurlplatform tool.\n - Sanitization: The risk is mitigated by mandatory manual steps, including an 'editorial and risk review' (Step 6) and a user approval process (Step 7) before any content is published or handed off.
Audit Metadata