video-content-strategist

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is composed of natural language instructions and frameworks for video production tasks. It does not include any scripts, external dependencies, or network-enabled tools.
  • [INDIRECT_PROMPT_INJECTION]: The skill includes instructions to read a local file, .claude/product-marketing-context.md, to gather project context.
  • Ingestion points: Reads a Markdown file within the local environment (.claude/product-marketing-context.md).
  • Boundary markers: None explicitly defined in the instruction set.
  • Capability inventory: No tool use or execution capabilities are defined in this skill; it is purely instructional.
  • Sanitization: None present.
  • While reading external files constitutes an indirect injection surface, the risk is negligible as the skill lacks any capabilities (such as file-write or network access) that could be exploited by malicious content within that file.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 02:11 PM
Security Audit — agent-trust-hub — video-content-strategist