The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requests access to the Bash tool to manage files and potentially execute local commands as part of the planning workflow. This is a standard capability for development-focused agents but requires user oversight during execution.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external sources into notes.md and task_plan.md, which creates an attack surface for indirect prompt injection.
Ingestion points: The skill reads untrusted data from the filesystem using Read, Grep, and Glob tools.
Boundary markers: No explicit delimiters or system instructions are provided to the agent to disregard instructions found within the processed files.
Capability inventory: The agent has access to Bash, Write, and Edit tools which could be exploited if malicious instructions are successfully injected into the planning files.
Sanitization: The skill does not implement sanitization or filtering of the content read from files before it is processed by the agent logic.

planning-with-files