The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requests the Bash(cmd:*) tool in its frontmatter, allowing the agent to execute any shell command. This is a high-privilege capability that, although common in documentation build workflows, should be used with caution as it allows for significant system access.
[INDIRECT_PROMPT_INJECTION]: Because this skill is intended to process external source code and documentation files (untrusted data) and has the power to execute shell commands and write files, it contains an inherent attack surface for indirect prompt injection. If an attacker places malicious instructions in the code comments or documentation being processed, they could potentially trigger unauthorized actions.

sdk-documentation-generator