The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core data-processing logic.
Ingestion points: Data enters the agent's context through WebFetch (external URLs) and the Read tool (local codebase files) as described in the 'Steps' section of SKILL.md.
Boundary markers: The instructions do not define delimiters or explicit warnings for the agent to disregard potential instructions embedded within the retrieved research data.
Capability inventory: The skill has access to powerful tools including Bash (shell access), Write (filesystem modification), and multiple memory storage tools (mcp__claude-flow__memory_store).
Sanitization: There is no requirement or mechanism mentioned to sanitize or validate the content fetched from external sources before it is used to influence further steps or stored in memory.
[COMMAND_EXECUTION]: The skill uses the Bash tool to execute shell commands such as grep and find for codebase analysis.
[EXTERNAL_DOWNLOADS]: The skill performs network operations using WebSearch and WebFetch to retrieve content from external domains during the research process.
[NO_CODE]: No external scripts, binaries, or executable files are included with this skill; it relies entirely on instructions and existing tools.

deep-research