optimization-advisor-sms
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill utilizes vendor-specific analytical tools (list_posts, get_post_analytics, get_follower_growth, get_recommendations) provided by the BlackTwist platform. These tools are used for read-only retrieval of social media performance data, which is consistent with the skill's primary function and the author's identity.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to its data ingestion requirements. 1. Ingestion points: The skill reads user niche, goals, and platform context from the .agents/social-media-context-sms.md file and incorporates findings from sibling skills (performance-analyzer-sms, etc.). 2. Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the retrieved data. 3. Capability inventory: The skill's capabilities are limited to analytical data retrieval via the BlackTwist MCP; it lacks file-writing, system-level execution, or external network operations beyond the vendor tools. 4. Sanitization: No specific validation or sanitization routines are mentioned for the ingested context data. The risk is assessed as safe because the ingestion is central to the skill's purpose and the available toolset is restricted.
Audit Metadata