The Agent Skills Directory

[SAFE]: The skill provides instructions for the agent to use local search tools to locate and read documentation files within the project directory. No malicious patterns, unauthorized network access, or credential harvesting were detected.
[COMMAND_EXECUTION]: The skill utilizes standard command-line tools such as rg, ls, and cat, alongside project-specific utilities like fff, qmd, and ctx. These tools are used for their intended purpose of navigating the file system and querying indexed documentation knowledge.
[INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data by reading project documentation (e.g., ADRs, wiki entries).
Ingestion points: Documentation files located in docs/, wiki/, configs/, and skills/ (SKILL.md).
Boundary markers: None explicitly defined within the skill instructions for separating search results.
Capability inventory: Uses rg, fff, qmd, ctx, cat, and ls for file discovery and reading (SKILL.md).
Sanitization: None specified for the content retrieved from documentation files.
Risk Assessment: While this represents an attack surface for indirect prompt injection if a documentation file contains malicious instructions, it is an inherent characteristic of document search tools and is typically managed by the agent's underlying safety guardrails.

doc-search