The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were found. The skill configuration is minimal and does not request any tool permissions or include executable logic.
[NO_CODE]: The skill contains no scripts, binaries, or logic files, which significantly limits the attack surface to purely instructional text.
[PROMPT_INJECTION]: The skill processes user-supplied plans for review, which represents a surface for indirect prompt injection.
Ingestion points: User-provided text describing plans or designs during the interaction specified in SKILL.md.
Boundary markers: No explicit delimiters or boundary markers are defined in the instructions.
Capability inventory: The skill has no associated tools, scripts, or network capabilities.
Sanitization: No sanitization is performed on input as there are no automated tools or scripts to invoke.

grill-me