The Agent Skills Directory

[EXTERNAL_DOWNLOADS] (LOW): The skill uses npx skills add to download and install external code packages. While this is the primary intended function of a scaffolding tool, the 'skills' package and its associated registry are not part of the pre-approved trusted organization list.
[COMMAND_EXECUTION] (LOW): The skill instructs the agent to execute shell commands (mkdir, touch, npx). The npx command specifically executes dynamic input ([required-skill]), which could be exploited if malicious input is provided to the agent.
[DATA_EXFILTRATION] (SAFE): No patterns related to accessing sensitive files (e.g., .ssh, .aws) or sending data to untrusted remote servers were detected.
[PROMPT_INJECTION] (SAFE): No instructions attempting to bypass safety filters, extract system prompts, or disregard previous instructions were identified.
[INDIRECT_PROMPT_INJECTION] (LOW): The skill presents an attack surface where untrusted data could influence command execution.
Ingestion points: File SKILL.md takes dynamic input for [required-skill] and [Role Name].
Boundary markers: Absent; there are no specific delimiters or instructions to ignore embedded commands within the input.
Capability inventory: File SKILL.md triggers shell command execution via npx.
Sanitization: Absent; the skill name is interpolated directly into the command line template.

scaffold