ingest-youtube
What this skill does
Ingest YouTube video transcripts into a markdown vault for downstream processing
github/sickn33 - Command Injection - 43.8k stars
Threat analysis
Skill info
pkg:github/sickn33/agentic-awesome-skills@11c9e67?skill=ingest-youtubeAssessments (2)
Command Injection
Command Injection via local-llm-review
ingest.py
The script uses subprocess.run with args passed directly from user input (the YouTube URL). If the URL contains malicious shell metacharacters, this could lead to command injection vulnerabilities.Insecure Temporary Files
Insecure Temporary Files via local-llm-review
ingest.py
The script uses tempfile but does not show explicit handling of temporary files. If temporary files are not properly secured, this could lead to information leakage or tampering.Badge
Add the Anomity scan badge for ingest-youtube 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 ingest-youtube? Report an issue or request a rescan.
