The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx to download and execute the @microsoft/learn-cli package from the NPM registry. This resource is provided by a trusted organization and is consistent with the skill's stated purpose.
[COMMAND_EXECUTION]: The skill relies on executing shell commands to search for, fetch, and display documentation content to the agent.
[INDIRECT_PROMPT_INJECTION]: The skill ingests content from external sources (Microsoft Learn documentation) which could potentially contain instructions aimed at influencing agent behavior.
Ingestion points: Documentation content retrieved via the fetch and search commands as described in SKILL.md.
Boundary markers: The skill does not explicitly define delimiters to separate fetched content from internal instructions.
Capability inventory: The skill has the capability to execute shell commands through the npx utility.
Sanitization: No specific filtering or sanitization of the retrieved documentation content is implemented beyond the manual warnings in the query safety section.

microsoft-learn-cli