reels-script
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill operates as a specialized content generation tool, focusing on marketing logic and script structure. Analysis shows no evidence of command execution, privilege escalation, or unauthorized network operations. Its primary function is to transform user-provided concepts into a production document for manual review or filming.\n- [INDIRECT_PROMPT_INJECTION]: The skill serves as an ingestion surface for untrusted data, which is a common characteristic of scriptwriting agents.\n
- Ingestion points: The skill processes user-supplied video concepts and reads external configuration files (
brand-profile.md,voice.md) in SKILL.md.\n - Boundary markers: There are no explicit instructions or delimiters used to isolate user-provided data from the agent's core instructions.\n
- Capability inventory: The skill references external capabilities for publishing and scheduling (e.g.,
instagram-reels-publishing) and b-roll generation via an API integration (tools/integrations/veo.md).\n - Sanitization: No data validation or sanitization routines are implemented for external inputs. However, because the final output is a text-based production script intended for human review, the risk is categorized as safe.
Audit Metadata