professional-word-output
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run several shell commands for document production, such as
pandocandpython scripts/create-reference-docx.py. It also references executing shell scripts (export-docs.sh) and PowerShell scripts (export-docs.ps1) for exporting deliverables. - [PROMPT_INJECTION]: The skill processes external Markdown source files as its primary input. It lacks explicit instructions to ignore embedded prompts or provide boundary markers, creating a surface for indirect prompt injection. This risk is assessed as low as it depends on the content of the ingested data (ingestion points: Markdown source files referenced in SKILL.md; boundary markers: absent; capability inventory: subprocess calls via pandoc, python, and bash mentioned in SKILL.md; sanitization: absent).
Audit Metadata