media-use
What this skill does
Media processing and generation (BGM, SFX, captions, transcription, etc.)
github/heygen-com - MCP Rug Pull - 40.4k stars
Threat analysis
Skill info
pkg:github/heygen-com/hyperframes@9734578?skill=media-useAssessments (3)
MCP Rug Pull
MCP Rug Pull via local-llm-review
audio/references/bgm.md
The skill relies on a 'Preflight' step to determine whether to use HeyGen's music catalog or fall back to local generation. This introduces a potential rug pull if the Preflight logic is manipulated oMCP Rug Pull via local-llm-review
audio/references/captions/authoring.md
The skill allows for per-word styling of captions, which could be used to inject malicious or misleading content if not properly validated.MCP Rug Pull via local-llm-review
audio/references/captions/transcript-handling.md
The skill supports multiple input formats for transcripts, including SRT and VTT, which may not be properly validated or sanitized, potentially allowing for injection of malicious content.Badge
Add the Anomity scan badge for media-use to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of media-use? Report an issue or request a rescan.
