The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized network activity were found in the skill file. The skill is primarily a documentation and routing layer for platform engineering tasks.
[INDIRECT_PROMPT_INJECTION]: The skill functions as a dispatcher, taking untrusted user input via the {{args}} placeholder and passing it to sub-skills. While this represents a potential attack surface for indirect prompt injection, it is a standard pattern for routing skills and does not contain malicious logic.
Ingestion points: The {{args}} variable in SKILL.md receives external input.
Boundary markers: No explicit delimiters or boundary instructions are used when interpolating input.
Capability inventory: The skill has access to powerful tools like Bash, Read, Write, WebFetch, and WebSearch as defined in the frontmatter configuration.
Sanitization: No input sanitization or validation is performed before routing to sub-skills.

pave