deconstruct
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of purely instructional markdown and basic agent configuration. No malicious code, obfuscation, or unauthorized access patterns were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill instructions involve analyzing external source code and live web pages to extract animation data, which creates a potential surface for indirect prompt injection from those untrusted sources.
- Ingestion points: Step 1 in
SKILL.mddirects the agent to analyze external source code and live pages. - Boundary markers: The instructions do not specify any delimiters or safety warnings for isolating content from external sources.
- Capability inventory: The skill is focused on generating data tables and reporting; it does not request or utilize tools for network requests, file system modification, or shell execution.
- Sanitization: There are no guidelines provided for sanitizing or escaping content retrieved from external sources.
Audit Metadata