inboundfy-validador-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 external content (YouTube scripts and metadata) which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The skill reads the 'asset' and 'brief' provided in the piece folder, including the script (roteiro) and description as specified in SKILL.md and REFERENCIA.md.
- Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the processed data files.
- Capability inventory: The skill is limited to content validation and reporting. It does not utilize tools for network access, file writing outside its scope, or shell command execution.
- Sanitization: No sanitization or filtering of the ingested content is mentioned in the provided instructions.
Audit Metadata