The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use curl to interact with a local service at http://127.0.0.1:8390 to fetch session data.
[COMMAND_EXECUTION]: The instructions direct the agent to ask the user for a local directory path and then execute scripts/svc-start.cmd from that location if the service is unavailable.
[DATA_EXPOSURE]: The skill accesses and displays historical session data from multiple agents (codebuddy, claude, codex, etc.), which may contain sensitive user information.
[INDIRECT_PROMPT_INJECTION]: The skill ingests and displays summaries and snippets from previous sessions, which could contain malicious instructions designed to influence the agent's behavior during retrieval.
Ingestion points: Session data is retrieved from local API endpoints (/api/search, /api/sessions) as described in SKILL.md.
Boundary markers: No delimiters or safety instructions are used to separate retrieved session content from the agent's instructions.
Capability inventory: The agent has the ability to execute shell commands (curl) and run local batch scripts (.cmd).
Sanitization: The skill does not mention any validation or sanitization of the content fetched from the session database.

find-session