text-to-excel
Pass
Audited by Gen Agent Trust Hub on Apr 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is subject to indirect prompt injection because it processes untrusted structured text from the user to generate a complex JSON configuration.
- Ingestion points: User-provided text, lists, and tables processed in SKILL.md Step 1.
- Boundary markers: Absent. The skill does not define specific delimiters or instructions to the agent to ignore embedded commands within the input text.
- Capability inventory: Execution of a Python script (
scripts/generate_excel.py) that writes to the local file system. - Sanitization: The skill relies on the agent's ability to parse text into the schema without providing explicit validation or sanitization rules for the input data.
- [COMMAND_EXECUTION]: The workflow involves executing a shell command to run a Python script with arguments.
- The command
python3 scripts/generate_excel.py <config.json> <output_path>uses an output path that is provided or confirmed by the user, which could result in writing files to unintended locations if the agent is misled.
Audit Metadata