The Agent Skills Directory

[SAFE]: The skill's behavior is consistent with its stated purpose; it accesses a specific local configuration file at ~/.claude/plugins/config/claude-for-legal/employment-legal/leave-register.yaml to manage leave deadlines.
[PROMPT_INJECTION]: The skill ingests untrusted data from external sources, which creates a surface for indirect prompt injection attacks.
Ingestion points: Reads data from a local YAML file and prompts users to upload spreadsheets for processing.
Boundary markers: None; the instructions do not implement markers or specific instructions for the agent to ignore content embedded within the records.
Capability inventory: The skill is limited to data retrieval and summarization; it does not possess network access, command execution, or file-writing capabilities.
Sanitization: No sanitization or validation of the input data is described or implemented.

leave-tracker