The Agent Skills Directory

[SAFE]: No malicious instructions, exfiltration patterns, or unauthorized access attempts were identified in the skill content or metadata.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface by design, as it ingests untrusted data from project files (Documentation, Diagrams, Web content, Data files, and Code) as specified in Step 1 of SKILL.md. Boundary markers and sanitization methods for this external content are not defined. The skill has the capability to modify project files using the Edit tool with replace_all (Step 3). However, the instructions focus on specific linguistic pattern matching and require user confirmation before any modifications, aligning with safe operational practices.

french-language