The Agent Skills Directory

[SAFE]: No security threats or malicious patterns were identified in the skill instructions or reference files.
[PROMPT_INJECTION]: The skill uses structured validation logic and does not contain instructions to bypass safety guidelines, jailbreak the model, or extract system prompts.
[DATA_EXFILTRATION]: The skill does not contain hardcoded credentials, network operations (curl, wget, etc.), or access patterns for sensitive system files.
[REMOTE_CODE_EXECUTION]: There are no patterns suggesting the download or execution of external scripts or unauthorized packages.
[INDIRECT_PROMPT_INJECTION]: Although the skill processes external input to generate a brief, it lacks high-privilege capabilities such as shell execution, file system modification, or network requests, which significantly limits the risk of exploitation.
Ingestion points: User-supplied brief fields (e.g., type, goal, audience) via conversational or agent-to-agent input (SKILL.md).
Boundary markers: None explicitly defined for the input YAML processing.
Capability inventory: The skill only returns structured text (YAML); it has no subprocess calls, file-write capabilities, or network operations.
Sanitization: None detected.

copy-brief