social-media-scheduling
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: Comprehensive analysis of the instructions, metadata, and evaluation prompts reveals no malicious patterns, code obfuscation, or persistence mechanisms. The skill is designed as a text-based planning assistant for marketing workflows.
- [PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it is designed to ingest and adapt user-provided source material into platform-native posts.
- Ingestion points:
SKILL.md(source material, campaign goals, audience descriptions). - Boundary markers: Absent; the skill does not instruct the agent to use specific delimiters or isolation markers for external data.
- Capability inventory: None; the skill's functionality is restricted to generating markdown text and lacks the ability to execute code, write to the filesystem, or make network requests.
- Sanitization: Absent; no explicit validation or filtering logic for processed content is described.
- [EXTERNAL_DOWNLOADS]: The documentation in the README.md and SKILL.md refers to external GitHub repositories for the purpose of skill installation and related tool discovery. These references are presented as standard installation instructions for the user and are not executed autonomously by the agent at runtime.
Audit Metadata