viral-scout
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions in
SKILL.mdandreferences/pattern-sheet.mdare purely instructional and focused on analyzing text patterns provided by the user. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input (social media hooks) as defined in
SKILL.md. - Ingestion points: User pastes examples of video hooks into the agent context.
- Boundary markers: None explicitly defined for the input content.
- Capability inventory: The skill has no capabilities to execute shell commands, perform network requests, or modify the file system.
- Sanitization: No sanitization is implemented, but the lack of dangerous tools makes the risk of exploitation negligible.
Audit Metadata