creator-campaign-ops
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill ingests data from external social media platforms (X, YouTube, TikTok, Instagram) via UnifAPI, which creates a surface for indirect prompt injection.
- Ingestion points: Social media posts, comments, and profiles retrieved through the unifapi skill.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore embedded commands in the ingested data.
- Capability inventory: The skill is restricted to read-only research and drafting operating packs; it does not have capabilities for command execution, file modification, or outbound network requests beyond data retrieval.
- Sanitization: No specific sanitization or filtering of external content is documented.
- [EXTERNAL_DOWNLOADS]: Installation instructions utilize the vendor's official plugin marketplace and domain (unifapi.com), which are recognized as authorized vendor resources.
- [DATA_EXFILTRATION]: The skill accesses local project context files, such as
.agents/product-marketing.md, to inform its campaign planning. This access is confined to the local environment and is necessary for the skill's stated marketing purpose.
Audit Metadata