dacast
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses the
@membranehq/clipackage from the NPM registry and references the official Membrane GitHub repository. These are verified resources associated with the skill's infrastructure. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the Dacast API (such as video metadata and stream descriptions), which constitutes a theoretical attack surface for indirect prompt injection from external content.
- Ingestion points: Data retrieved from Dacast via actions like
list-videosorlookup-stream(SKILL.md). - Boundary markers: None identified in the provided instructions.
- Capability inventory: Shell command execution via the
membraneCLI and network proxy requests (SKILL.md). - Sanitization: No explicit sanitization or filtering of API responses is mentioned.
Audit Metadata