The Agent Skills Directory

[NO_CODE]: The skill consists entirely of Markdown instructions and does not include any executable scripts, binaries, or source code files.\n- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access commands were identified. The skill is designed to enhance security by instructing the agent to check for exposed secrets and validate environment configurations.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface (Category 8) because it processes untrusted project data such as spec.md and application source code. This surface is inherent to its primary function as an integration evaluator and does not represent malicious intent by the author.

eval-integration