The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes implementation code and contract files which constitute an external data ingestion surface that could be exploited to influence the agent's behavior.
Ingestion points: The skill reads content from contracts/, src/, backend/, frontend/, and docs/ directories via the shared_read configuration and Read/Grep tools.
Boundary markers: The instructions lack specific requirements for using delimiters or "ignore embedded instructions" warnings when handling the content of these files during the audit process.
Capability inventory: The skill is granted access to Read, Write, Grep, Glob, and Bash tools, allowing it to perform extensive file operations and search tasks based on its findings.
Sanitization: There are no explicit instructions for sanitizing or escaping the content retrieved from external source files before it is processed or interpolated into the contract-audit.md report.

contract-auditor