sponsorship-prospecting
Pass
Audited by Gen Agent Trust Hub on Nov 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data retrieved from YouTube channel and video metadata.
- Ingestion points: The agent reads channel descriptions, video titles, and descriptions as described in the Workflow (steps 4 and 5) of
SKILL.md. - Boundary markers: Absent. The skill does not provide instructions to use specific delimiters or to disregard instructions that might be embedded within the external YouTube content.
- Capability inventory: The skill is designed for data aggregation and reporting in Markdown and CSV formats. It does not include capabilities for arbitrary command execution, sensitive file system access, or network exfiltration.
- Sanitization: Absent. There are no instructions to sanitize, escape, or filter the external text retrieved from the YouTube API before it is processed or included in the final output.
Audit Metadata