The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill retrieves document bodies using the openplan doc get command, which allows external, potentially untrusted data to enter the agent's context.
Ingestion points: Document content is fetched via the openplan doc get command as instructed in SKILL.md.
Boundary markers: There are no explicit delimiters or instructions provided to help the agent distinguish between its own system instructions and the content within the documentation.
Capability inventory: The agent has the ability to modify, create, and delete documents via the openplan CLI, and can navigate browser interfaces using tools like mcp__Claude_Browser__navigate or @Browser.
Sanitization: The skill does not include instructions for sanitizing or validating document content before the agent processes it.
[COMMAND_EXECUTION]: The skill directs the agent to execute shell commands using the openplan binary, including operations like $(cat body.md) which involve direct file system reading and command interpolation.

openplan-docs