inboundfy-especialista-youtube
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from external briefs and assets, which creates a potential surface for indirect prompt injection. However, this is inherent to its primary purpose of content generation.
- Ingestion points: The skill ingests data from local files within the
briefs/andacervo/directories, as well as editorial context from.inboundfy/context/. - Boundary markers: The skill architecture utilizes structured YAML frontmatter (defining ID, state, and sources) and specific Markdown headers to separate processing instructions from the raw data being transformed.
- Capability inventory: The skill's capabilities are limited to reading project files and writing content to the specific
canais/youtube/directory. No network operations, system-level command execution, or dynamic execution primitives were detected. - Sanitization: While no automated sanitization is described, the workflow mandates a validation step through the
inboundfy-validador-youtubeskill to ensure consistency with defined personas and brand voice.
Audit Metadata