The Agent Skills Directory

[PROMPT_INJECTION]: The skill enables the agent to read messages from external Slack channels, which creates a surface for indirect prompt injection (Category 8).
Ingestion points: The readMessages action ingests untrusted text directly from Slack channel history into the agent's context.
Boundary markers: The documentation does not specify the use of delimiters or instructions for the agent to ignore potentially malicious instructions embedded within retrieved messages.
Capability inventory: The skill provides significant capabilities, including sendMessage, editMessage, deleteMessage, and pinMessage, which could be triggered by instructions found in ingested data.
Sanitization: There is no evidence of sanitization, filtering, or validation of the message content before it is processed by the agent.
[NO_CODE]: The skill consists entirely of documentation and configuration for a pre-existing slack tool. It does not include any executable scripts, binaries, or third-party package dependencies.

slack