T09 · Insecure Skill Coding Practices
- Location
SKILL.md:103- Finding
Command Injection Through Unsafe Inline Python Interpolation
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This skill is openly about releasing albums, but it can trigger public publishing, radio deployment, service restarts, and social posts without clear approval gates.
Review this skill before installing if an agent will have access to real music, video, social, OAuth, radio, SSH, or cron-sourced credentials. Use it only with explicit release intent, require manual approval before uploads, deployment, service restart, playlist creation, premiere, and social posting, and audit any runner so JSON config is parsed as data rather than interpolated into Python source.
SKILL.md:103Command Injection Through Unsafe Inline Python Interpolation
The skill is framed for broad, one-run end-to-end release automation without strong activation boundaries or confirmation gates. In a system where agents may invoke skills from natural-language intent, this can cause accidental execution of high-impact actions like publishing, deployment, and announcement from underspecified user requests.
The skill includes public publishing, radio deployment, playlist creation, and social fanout behavior, but it does not present an explicit warning that these steps create irreversible or externally visible side effects. This increases the risk of accidental public release, unwanted posts, or premature distribution if the skill is triggered in the wrong context or run with incomplete review.