The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions to execute a local Python script (generate_schematic.py) via the Bash tool to automate diagram generation. This script is part of an integrated diagramming skill and operates on local paths.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface due to its core function of researching external technology documentation.
Ingestion points: Untrusted data is retrieved from external websites using WebSearch and WebFetch tools as specified in SKILL.md.
Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands within the researched content.
Capability inventory: The skill has access to Bash, Write, and Edit tools, which could be targeted if the agent follows instructions found in external data.
Sanitization: There is no mention of sanitizing or filtering the content retrieved from the web before the agent processes it.

architecture-research