The Agent Skills Directory

[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) due to its core function of analyzing external codebases.
Ingestion points: The skill reads various project files, including source code (.php, .tsx, .py) and configuration files (package.json, composer.json, requirements.txt), to identify frameworks and patterns.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the processed files are specified in the instructions.
Capability inventory: The skill utilizes powerful tools including Read, Grep, Glob, and Bash to perform its analysis.
Sanitization: There are no mentions of sanitizing or escaping the content read from the codebase before it is processed by the agent, allowing malicious instructions in the code to potentially influence agent behavior.

codeprobe-framework