The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests user financial details and risk factors to populate command-line arguments for a local execution script. Ingestion points: User-provided values for essential monthly spend, current savings, and risk profile flags as defined in SKILL.md. Boundary markers: None explicitly present in the skill instructions to separate user data from command context. Capability inventory: Executes the local file scripts/emergency_fund.py using shell command interpolation. The script itself is restricted to standard Python libraries (argparse, json, sys) and does not perform network operations or file writes. Sanitization: The calculation script performs basic type validation (floats and booleans) via the argparse library, which helps prevent malformed input but does not mitigate all prompt injection vectors.
[COMMAND_EXECUTION]: The primary functionality of the skill relies on executing a bundled Python script. This script is contained within the skill package and does not require administrative privileges or access to sensitive system resources.

emergency-fund