social-media-generator
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFE
Full Analysis
- [Indirect Prompt Injection] (SAFE): The skill identifies a data ingestion surface where user-provided event details are used to generate content and filenames.
- Ingestion points: User-provided event names, dates, and messages in SKILL.md Step 1.
- Boundary markers: Absent; instructions do not specify delimiters for user-supplied content.
- Capability inventory: Local file-write operations as described in SKILL.md Step 4.
- Sanitization: Absent; the skill relies on the agent's internal safety filters.
- [External Downloads] (SAFE): No external packages or remote code execution patterns were detected in the package.json or index.js files.
Audit Metadata