social-content-creation
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external source material (e.g., newsletters, articles, and podcast transcripts) to extract insights and generate social media posts. \n
- Ingestion points: Phase 1 involves reading and extracting concepts from user-provided source material (SKILL.md). \n
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded prompts within the ingested material, which could lead to unintended agent behavior if the source contains malicious instructions. \n
- Capability inventory: The skill is limited to text analysis and document generation; it does not utilize sensitive system tools, network operations, or shell execution (SKILL.md). \n
- Sanitization: No explicit sanitization or filtering of the input source material is described in the workflow.
Audit Metadata