The Agent Skills Directory

[SAFE]: No security issues were detected. The skill consists entirely of instructional markdown files without any associated scripts, executables, or external dependencies.
[SAFE]: No instances of direct prompt injection, credential exposure, or obfuscation were found.
[SAFE]: The skill processes untrusted external data such as call transcripts and email threads (Ingestion points: SKILL.md). While there are no explicit boundary markers or sanitization logic defined, the skill does not possess any capabilities (Capability inventory: None) that could be exploited by an injection attack. The risk is limited to the conversational context.

voss-advisor