The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from the user's project codebase to identify security vulnerabilities.
Ingestion points: The skill reads project source files, HTML templates, and configuration files located in ${CLAUDE_SKILL_DIR}/ (defined in SKILL.md).
Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between code to be analyzed and potential instructions embedded in comments or metadata within the scanned files.
Capability inventory: The skill has access to powerful tools including Read, Write, Edit, Grep, and Bash scoped to security, scan, and audit functions (defined in SKILL.md).
Sanitization: The provided Python script (scripts/csrf_test.py) performs basic file checks (size and JSON validation) but does not implement sanitization or filtering of the content read from the files before it is processed by the agent.

validating-csrf-protection