opusclip
Warn
Audited by Snyk on May 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill accepts arbitrary public video URLs (e.g., "opusclip submit --url" in SKILL.md) and its runtime scripts (scripts/opusclip: cmd_describe, cmd_preview, cmd_storyboard, cmd_trim) fetch/export clip metadata and transcripts via the API and even download preview videos (curl "$preview_url"), which the agent reads and uses to generate copy/post or take follow-up actions—exposing it to untrusted user-generated web content that could carry indirect instructions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata