The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The scripts/check_version.py script connects to raw.githubusercontent.com to fetch a configuration file from the author's (plainlang) repository to check for updates. This is a standard update check using a well-known service.
[DYNAMIC_EXECUTION]: In Step 4.3, the skill instructs the agent to execute the generated conformance and unit tests. This involves running code that was dynamically created by the agent based on input specifications. This is an expected behavior for a code rendering and testing tool.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from .plain specification files to generate code and tests. This creates a surface for indirect prompt injection if the specification files contain adversarial instructions designed to influence the agent's output.
Ingestion points: The agent reads specification files using the scripts/plain_sections.py utility in Step 1, Step 3.1, and Step 4.1.
Boundary markers: There are no specific delimiters or instructions provided to the agent to ignore potential instructions embedded within the specification content.
Capability inventory: The agent has the ability to write files to the local directory, copy folders, and execute Python scripts including the generated test suites.
Sanitization: The skill does not implement sanitization or validation of the specification content before processing it for code generation.

render-spec