The Agent Skills Directory

[SAFE]: The skill does not contain any malicious instructions, prompt injections, or attempts to bypass safety filters. Its instructions are focused on legitimate performance analysis tasks.- [SAFE]: No obfuscation techniques, such as Base64 encoding or hidden characters, were identified in the skill content.- [SAFE]: There are no requests for sensitive files, credentials, or external network access. The skill operates entirely within the context of analyzing the local repository.- [SAFE]: While the skill references a project documentation file (docs/perf-requirements.md), which is a theoretical surface for indirect prompt injection, the skill itself does not define any high-risk capabilities (like command execution or network exfiltration) that would allow such an injection to be exploited.

perf-code-paths