The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions direct the agent to execute a local Python script located at scripts/check.py. This script performs mechanical linguistic checks on documentation using the Python standard library and regular expressions to identify vague words, passive voice, and incorrect punctuation. This is a primary function of the skill and does not involve remote code execution or network operations.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and rewrite technical documentation provided by the user, creating a surface for potential indirect prompt injection attacks.
Ingestion points: The agent ingests untrusted text from technical documents (READMEs, design docs, code comments) as specified in the Workflow section of SKILL.md.
Boundary markers: The skill does not explicitly define delimiters to isolate user-provided content from instructions, though it uses references/output-template.md to structure the final output.
Capability inventory: The skill involves local script execution for linting and file-writing capabilities to deliver rewritten documentation.
Sanitization: There is no evidence of explicit sanitization or filtering of the input text before it is processed by the agent or the check script.

hai-simplified-technical