The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses grep and ripgrep to search the local filesystem. These commands are used for code analysis and are limited to specific project directories such as packages/ and apps/.
[INDIRECT_PROMPT_INJECTION]: The skill involves analyzing external codebase content, which presents a surface for indirect prompt injection. Ingestion points: The output of grep and ripgrep commands executed against the local codebase as described in SKILL.md. Boundary markers: Absent. The instructions do not define specific delimiters for separating code output from instructions. Capability inventory: The skill relies on local search utilities (grep, ripgrep) for analysis (SKILL.md). No network operations, file-writing, or dynamic code execution capabilities are defined in the skill. Sanitization: Absent. There are no explicit instructions to sanitize or validate the content retrieved from the codebase.

code-audit