video
Pass
Audited by Gen Agent Trust Hub on Apr 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest data from an external source, specifically the
.agents/product-marketing-context.mdfile, which represents an indirect prompt injection surface. - Ingestion points:
.agents/product-marketing-context.mdand.claude/product-marketing-context.md(mentioned in SKILL.md). - Boundary markers: None. The instructions do not provide delimiters or warnings to ignore embedded instructions within the context file.
- Capability inventory: The skill provides instructions for scriptwriting and video tool recommendations. It does not contain scripts that perform automated file writes, network exfiltration, or direct subprocess execution based on the ingested content.
- Sanitization: None. The content is used directly to inform the agent's persona and script generation logic.
Audit Metadata