The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external Discord channels, creating a risk that instructions embedded in messages could be executed by the agent.
Ingestion points: Message content retrieved from Discord channels via discord.readMessages as described in SKILL.md.
Boundary markers: Absent; the instructions do not include delimiters or specific guidance for the agent to ignore instructions found within the retrieved messages.
Capability inventory: The skill utilizes memory-edit to write summarized data to the /memory/discord/ directory on the local file system.
Sanitization: Absent; there is no mention of filtering, escaping, or validating the external message content before it is parsed and stored.

lurk