script-structure
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions include a step to read a local file (
.agents/youtube-context.md) to guide the script's tone and formatting. This represents a potential surface for indirect prompt injection if that file is attacker-controlled. - Ingestion points: Reads channel context, format, and audience details from
.agents/youtube-context.md(SKILL.md). - Boundary markers: No explicit delimiters or 'ignore embedded instructions' warnings are provided for the content of the context file.
- Capability inventory: The skill is restricted to text generation and lacks capabilities for network access, file writing, or command execution.
- Sanitization: No sanitization or validation of the context file content is performed.
Audit Metadata