The Agent Skills Directory

[SAFE]: No malicious patterns detected. The skill performs legitimate feature activation tasks such as validating codes and updating configuration files.
[DATA_EXPOSURE]: The skill accesses local system configuration files (System/beta-features.yaml and System/user-profile.yaml) to manage feature flags and user profiles. This is necessary for the skill's functionality.
[PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection by fetching and displaying content from beta instruction files.
Ingestion points: Content returned by the get_beta_instructions tool is displayed in Step 5.
Boundary markers: No explicit delimiters or instructions are used to separate the external content from the agent's instructions.
Capability inventory: The skill calls validate_beta_code, activate_beta_feature, track_event, and get_beta_instructions tools.
Sanitization: No evidence of sanitization or filtering of the instruction content before display is provided.

beta-activate