biz-dev-social-media-audit-offer
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of instructional markdown and reference materials. No executable scripts, binary files, or suspicious shell commands are present. The workflow is restricted to information gathering and report generation.\n- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it instructs the agent to process data from external social media accounts (bios, posts, and analytics). Ingestion points: Prospect social media profiles and content (SKILL.md). Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore embedded commands in the audited content. Capability inventory: The skill is limited to generating markdown documents and does not have write access to the audited accounts or network capabilities. Sanitization: No sanitization steps are defined for the external content before it is incorporated into the findings report. This surface is inherent to the audit task and represents a minimal security risk in this context.
Audit Metadata