The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes content from external, untrusted sources such as Slack threads and meeting transcripts. Ingestion points: Content is ingested through tools like meeting.get, meeting.get_transcript, and slack.search_threads. Boundary markers: Absent; there are no instructions for the agent to use delimiters or ignore embedded commands in the retrieved data. Capability inventory: The skill allows retrieval of organizational data and the creation of task proposals. Sanitization: Absent; no data cleaning or escaping methods are described for handling external input.
[NO_CODE]: This skill consists entirely of instructional markdown and does not contain any executable scripts, binaries, or configuration files that run on the host system.

collabute-mcp