The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and analyze untrusted data from an existing codebase to generate documentation. Ingestion points: Behavior step 1 involves surveying repository source modules, public interfaces, and existing documentation files (SKILL.md). Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the processed files are defined. Capability inventory: The skill uses shell commands (mkdir, touch) and writes files to the docs/ directory based on the analyzed content. Sanitization: No evidence of sanitization or filtering of the ingested content before it is used to generate artifacts.

project-adopt