The Agent Skills Directory

[NO_CODE]: The skill consists of a markdown instruction file and metadata without any associated executable scripts or binary files.
[PROMPT_INJECTION]: The skill definition possesses an attack surface for indirect prompt injection via the ingestion of untrusted external data.
Ingestion points: The skill utilizes the WebSearch and WebFetch tools to retrieve information from external, potentially attacker-controlled websites.
Boundary markers: There are no delimiters or specific safety instructions provided to the agent to differentiate its primary instructions from content fetched from the web.
Capability inventory: The agent is granted Write access to the filesystem and WebFetch network capabilities, which could be leveraged if the agent is influenced by malicious instructions in fetched content.
Sanitization: No sanitization or validation of the content retrieved from the web is specified within the skill definition.

executive-cmo