The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface by taking untrusted user input (e.g., salary, years of employment, and salary history) and interpolating it into a shell command to execute a local script.
Ingestion points: User-provided values for employment factors, salary, and tenure history in SKILL.md (Step 1 and Step 6).
Boundary markers: Absent; the instructions do not provide delimiters or instructions for the agent to sanitize or ignore embedded instructions within the user input.
Capability inventory: The skill utilizes the Bash tool to execute a bundled Python script (scripts/severance-calculator.py) for processing the data.
Sanitization: No explicit validation or sanitization logic is provided in the agent instructions to handle potentially malicious user input before it is passed to the shell.
[COMMAND_EXECUTION]: The skill instructs the agent to use the Bash tool to run a local Python script provided in the skill bundle to perform severance pay calculations.
Evidence: Multiple instructions to run python3 scripts/severance-calculator.py with user-supplied arguments in SKILL.md and SKILL_HE.md.

israeli-workplace-rights-navigator