The Agent Skills Directory

[Indirect Prompt Injection] (LOW): The skill is susceptible to indirect prompt injection because it processes untrusted code or content provided in the target argument. Ingestion points: The target parameter in SKILL.md allows the agent to read files or system behavior. Boundary markers: The instructions do not include delimiters or specific commands to treat the analyzed content as data only, which could lead the agent to follow instructions embedded in the analyzed code. Capability inventory: The skill leverages tools including Read, Grep, and Bash for analysis. Sanitization: No sanitization or validation of the input content is specified before processing.
[Command Execution] (SAFE): The skill utilizes Bash for runtime behavior analysis. This is a powerful capability, but it is necessary for and limited to the skill's primary purpose of explaining system behavior.

sc-explain