data-data-platform
Warn
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: MEDIUMPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill's reference documentation (e.g.,
architecture-patterns.md,code-organization.md,deployment-pipelines.md, etc.) contains an extreme volume of repetitive filler text. Each file contains 150 sections that cycle through the same 5-10 technical paragraphs thousands of times. This technique creates a massive context window that obscures content and can hinder effective security auditing by hiding instructions within a wall of noise. - [PROMPT_INJECTION]: Deceptive documentation practices. The reference files are labeled as "Ultimate Deep Dives" intended for "Staff+ Engineers," but the content is low-value, repetitive technical boilerplate. This misleading framing can cause users to misjudge the maturity and safety of the skill.
- [EXTERNAL_DOWNLOADS]: The skill's examples reference external container images (
ghcr.io/org/spark-iceberg,myrepo/spark-py) and Git repositories (github.com/org/data-pipelines.git). Although these are placeholders (using 'org'), they represent points where external code is introduced into the environment and must be verified before deployment.
Audit Metadata