The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Python script, scripts/generate_questionnaire.py, to generate Excel-based questionnaires. This is a core part of the skill's functionality and utilizes the openpyxl library.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by processing untrusted data from user-supplied files and local configuration graphs. Ingestion points: Processes plans/docs-graph.json, user-provided .xlsx files (via the --answers flag), and .pdf requirements documents. Boundary markers: No delimiters or specific instructions to ignore embedded commands were found in the templates or processing logic. Capability inventory: The skill has the ability to write files to the local plans/ directory and execute a local Python script. Sanitization: No evidence of sanitization or validation of the content extracted from external files was detected.
[EXTERNAL_DOWNLOADS]: The skill uses the WebSearch tool in Phase 2 to gather industry patterns and documentation links, which are saved to references.md.

debrief