The Agent Skills Directory

[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests data from external XML files and presents it to the agent without sanitization or boundary markers.
Ingestion points: The script scripts/form-info.ps1 reads the file specified in the -FormPath argument.
Boundary markers: Absent. The output uses simple text headers (e.g., Elements:, Attributes:) but does not include explicit delimiters or instructions for the agent to ignore potential commands embedded within the XML content.
Capability inventory: The agent has access to Bash, Read, and Glob tools, which could be misused if the agent is manipulated by instructions hidden in a malicious Form.xml file.
Sanitization: None. The script extracts text from XML nodes (like Titles or Names) and outputs them directly to the console via Write-Host.

form-info