short-drama-skill-finder
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches a project database from
https://shortdramaskills.com/data.jsonand a fallback README from the author's GitHub repository (UnderleveledBuilder/awesome-short-drama-skills). These resources are used to provide the user with a curated list of relevant tools and skills. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data to generate its recommendations, creating a potential surface for indirect injection.
- Ingestion points: Data is fetched from remote JSON and Markdown files via URLs in
SKILL.md. - Boundary markers: The instructions include a mandatory safety reminder for the user to review a skill's
SKILL.mdbefore installation and explicitly state not to run commands without user consent. - Capability inventory: The skill itself does not perform any file system writes, subprocess execution, or unauthorized network operations.
- Sanitization: The skill implements logic to filter the external data (e.g., dropping archived items and platform apps) and restricts output to specific structured fields.
Audit Metadata