The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. Ingestion points: Data is read from CHANGELOG.md, plugin.json, and various documentation files across the docs/, book/, and plugin directories. Boundary markers: None are present; the skill does not use delimiters or instructions to ignore embedded commands in the source data. Capability inventory: The skill has access to Bash, Write, and Edit tools, allowing it to modify or delete files. Sanitization: No sanitization or validation of the ingested content is performed before it is used to influence documentation edits.
[COMMAND_EXECUTION]: The skill relies on the Bash tool for several complex auditing and synchronization tasks. Evidence: Shell commands and scripts using jq, find, grep, awk, and comm are used to query project status and manage temporary files during the synchronization process.

doc-updates