The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local codebase, which presents a surface for indirect prompt injection.\n- Ingestion points: The skill reads local files using 'clj-kondo', 'ripgrep' (rg), and 'ast-grep' as described in 'SKILL.md'.\n- Boundary markers: Absent. There are no explicit instructions or delimiters provided to the agent to distinguish between the skill's instructions and the untrusted content being processed.\n- Capability inventory: The skill utilizes the 'Bash' tool for executing CLI commands and the 'Edit' tool for modifying files on the system.\n- Sanitization: Absent. The skill does not perform any sanitization or validation of the code content before it is displayed to or processed by the agent.

code-rename