The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local shell commands to facilitate its workflow, including npx vigiles generate types for discovery, and npm run build and npx vigiles compile for verifying that modifications do not break the project build.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection because it reads and processes external data that could be controlled by an attacker (e.g., via a malicious pull request).
Ingestion points: The agent reads the contents of **/*.md.spec.ts files and documentation files located in ../linter-docs/ to find and match rules.
Boundary markers: The instructions do not specify the use of delimiters or specific markers to prevent the agent from following instructions that might be embedded within the project's specification or documentation files.
Capability inventory: The skill has significant capabilities, including executing shell commands via npm/npx, modifying source code and configuration files, and committing changes to the repository.
Sanitization: There is no evidence of sanitization, filtering, or validation of the content ingested from the external markdown and specification files.

strengthen