The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and parses the content of Technical.md files to extract rules for validation. This external content is untrusted and could contain instructions designed to override the agent's behavior.
Ingestion points: Processes Technical.md and ./.candid/Technical.md files.
Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the processing logic.
Capability inventory: Employs ls, find, and grep commands to interact with the filesystem based on patterns found in the analyzed documentation.
Sanitization: The skill does not explicitly define sanitization or escaping mechanisms for data extracted from the target files before using it in shell-based verification tasks.
[COMMAND_EXECUTION]: The skill performs active filesystem reconnaissance using standard shell utilities.
Evidence: Uses ls to detect linter configuration files (e.g., .eslintrc, pyproject.toml, .rubocop.yml) and to verify the existence of paths cited in rules.
Evidence: Utilizes find and grep in Step 4.6 to sample files and check for rule compliance within the codebase.

candid-validate-standards