video-content-strategist

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists of instructional markdown content and metadata. It does not contain any executable scripts, shell commands, or network operations.
  • [PROMPT_INJECTION]: Analysis for direct prompt injection patterns (e.g., bypass markers, role-play instructions, or system prompt extraction) returned no findings.
  • [DATA_EXPOSURE]: The skill suggests reading a file named marketing-context.md to gather business context. No attempts to access sensitive system directories, credentials, or environment variables were detected.
  • [PROMPT_INJECTION]: The skill has an ingestion surface for untrusted data via marketing-context.md (Category 8: Indirect Prompt Injection). However, the skill lacks any dangerous capabilities (such as network access or shell execution) that could be exploited by malicious content within that file.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 08:15 PM
Security Audit — agent-trust-hub — video-content-strategist