write-weekly-report
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes output from "all upstream skills" and external CSV files (e.g.,
substack-stats-YYYY-MM-DD.csv). While this creates a surface for indirect prompt injection, the skill's instructions strictly constrain the output to a specific YAML schema and markdown structure, which limits the potential for malicious instruction execution. - Ingestion points: Upstream skill outputs and Substack stats CSV files defined in the workflow.
- Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are defined for the ingested data.
- Capability inventory: The skill is authorized to write markdown files to specific paths (e.g.,
substack/final ops/growth-analyst/YYYY-WW-report.md). - Sanitization: The skill does not specify any sanitization or escaping protocols for the external content before it is interpolated into the final report.
Audit Metadata