youtube-publishing-and-metadata
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from video scripts and brand profiles, which creates a surface for indirect prompt injection if those inputs contain malicious instructions intended to manipulate the agent's output.
- Ingestion points: The skill is instructed to read external content including
brand-profile,goals-and-kpis, and video scripts (as described in SKILL.md). - Boundary markers: There are no specific instructions or delimiters defined to isolate or ignore instructions that might be embedded within the input scripts or profiles.
- Capability inventory: The skill has the capability to write and configure publishing parameters (title, description, tags, category, and legal flags) for the WoopSocial tool, which then publishes directly to YouTube (SKILL.md).
- Sanitization: The skill instructions do not specify any validation, escaping, or sanitization processes for the text extracted from input scripts before it is used to generate metadata.
Audit Metadata