The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests and processes potentially untrusted data from external Plane API responses, including issue descriptions and comment threads, to generate behavioral insights. This ingestion represents a surface for indirect prompt injection if an attacker-controlled issue contains malicious instructions.
Ingestion points: Plane API data retrieved via mcp__plane__list_project_issues, mcp__plane__get_issue_comments, and other issue-detail tools.
Boundary markers: The analyst agent instructions do not specify the use of delimiters or 'ignore' instructions to isolate Plane data from the agent's core logic.
Capability inventory: The skill is restricted to Bash(jq:*), Bash(date:*), Read, and AskUserQuestion tools.
Sanitization: No explicit sanitization or filtering of API response content is documented before processing by the LLM.
[SAFE]: The skill references the domain projects.intentsolutions.io for its API host configuration. This domain is owned by the skill's author (jeremy@intentsolutions.io) and is documented neutrally as the default environment for the tool's behavioral synthesis functions.

plane