video-marketing
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of markdown-based instructions for generating video marketing strategy and scripts. No scripts, binaries, or command-line tools are included in the skill package.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest data from external project files to align with the user's project context. This surface is evaluated as safe due to the lack of exploitable capabilities within the skill.
- Ingestion points: Reads
.claude/project-context.mdand.cursor/project-context.md(specified in SKILL.md). - Boundary markers: No specific delimiters or "ignore instructions" warnings are applied to the ingested content.
- Capability inventory: No dangerous capabilities (network operations, shell command execution, or file writing) were detected in the skill content.
- Sanitization: No explicit sanitization or validation of the external project data is performed.
Audit Metadata