pm
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes
curland theghCLI to interact with third-party APIs (Notion, Plane, Linear) and GitHub. These operations execute shell commands that incorporate sensitive environment variables like$NOTION_API_KEYand$PLANE_API_KEY. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its processing of untrusted data from external sources.
- Ingestion points: Project card titles, descriptions, and comments are fetched from various external PM tools and local Obsidian files.
- Boundary markers: The instructions do not define clear boundaries or provide guidance to the agent to disregard instructions found within the project data.
- Capability inventory: The skill has access to network tools (
curl), authenticated CLI tools (gh), and can perform local file system writes to configuration files. - Sanitization: Content retrieved from external platforms is interpolated directly into the workspace context without sanitization or validation.
Audit Metadata