create-tdd
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from project artifacts like PRDs and tickets to generate designs, creating a surface where instructions in those documents could influence agent behavior.
- Ingestion points: The skill reads all relevant artifacts in the task directory as instructed in SKILL.md.
- Boundary markers: No explicit delimiters or instructions to ignore embedded content are specified for the ingestion process.
- Capability inventory: The skill performs file system operations (read, write, ls) and executes git commands (rev-parse).
- Sanitization: No specific content filtering or validation is implemented for the ingested text.
- [EXTERNAL_DOWNLOADS]: The skill's HTML template references external resources from a well-known service for styling.
- Evidence: The file references/artifact_template.html imports 'IBM Plex Mono' from Google Fonts via an @import rule.
Audit Metadata