after-hours-editorial-template
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines an interaction workflow that ingests untrusted text parameters while possessing file modification permissions.
- Ingestion points: Reads layout parameters and color configurations from the workspace
DESIGN.mdfile during initialization. - Boundary markers: No isolation mechanisms or parsing constraints are established to counter instructions embedded within the ingested configuration file.
- Capability inventory: Configured with the
file_writecapability inSKILL.mdfrontmatter to output the finalindex.htmlasset. - Sanitization: Lacks data validation checks or sanitization routines prior to converting layout configuration values into inline CSS template variables.
Audit Metadata