The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute specific bash scripts located at /Users/inoueyousuke/.claude/skills/cosense/scripts/cosense_api.sh to perform operations like fetching page text and searching.
[EXTERNAL_DOWNLOADS]: The helper scripts perform network operations to retrieve content from external Cosense pages.
[PROMPT_INJECTION]: The skill processes untrusted data from external pages, creating an indirect prompt injection surface.
Ingestion points: Data is fetched from external Cosense pages via the get-page-text and get-page commands.
Boundary markers: No specific delimiters or instructions are used to distinguish the fetched external data from the agent's core instructions.
Capability inventory: The agent can execute shell scripts and access external network data.
Sanitization: The retrieved content is not sanitized or validated before being analyzed by the agent.

secretary