The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and parse untrusted legal text (submissions, briefs, and AI-generated drafts) to extract citations.
Ingestion points: Legal text documents containing Singapore court citations (processed as described in the Input section of SKILL.md).
Boundary markers: The instructions do not specify any delimiters or safety markers to isolate the untrusted citation text from the agent's logic.
Capability inventory: The skill has the capability to execute shell commands (via npx) and perform network lookups (to eLitigation).
Sanitization: There is no mention of input validation or sanitization of the extracted strings before they are used in tool operations.
[EXTERNAL_DOWNLOADS]: The skill documentation suggests the use of the npx sgcite command. This involves downloading and executing the 'sgcite' package from the npm registry, a well-known public package repository.
[COMMAND_EXECUTION]: The primary function of the skill is carried out through the execution of a command-line tool (npx sgcite check), which interacts with the local file system and external network resources.

sgcite