campaign-review

Pass

Audited by Gen Agent Trust Hub on Oct 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes social media drafts which could contain instructions designed to influence the agent's behavior. Ingestion points: The skill retrieves draft content using social_getSocialMediaDrafts in SKILL.md. Boundary markers: The instructions do not specify the use of delimiters or clear boundaries when presenting draft content. Capability inventory: The agent has capabilities to update drafts (social_updateSocialMediaDraft) and create review bundles, as well as hand off to scheduling tools. Sanitization: There are no explicit instructions to sanitize or escape the content of the drafts before processing.
  • [EXTERNAL_DOWNLOADS]: The skill connects to a hosted MCP (Model Context Protocol) server for social review workflows. The configuration in agents/openai.yaml specifies a tool dependency at https://apikit.simplified.com/mcp.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 22, 2026, 11:53 AM