The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The scripts/api_validator.py script identifies and reads files within a target project directory to validate API design patterns. This creates a surface for indirect prompt injection, as an agent processing the script's output could be influenced by malicious content embedded in the scanned files.
Ingestion points: The script uses Path.glob to find and read file content from various paths such as **/routes/* and **/*api* in scripts/api_validator.py.
Boundary markers: The script output does not include explicit delimiters or instructions for the agent to ignore content from the files being analyzed.
Capability inventory: The skill is configured with allowed-tools including Read, Write, Edit, Glob, and Grep in SKILL.md.
Sanitization: The script performs regex matching and JSON parsing but does not sanitize the content before reporting validation results, which are then processed by the agent.

api-patterns