freedcamp
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends installing the
@membranehq/clipackage from NPM. This tool is provided by the skill's author to manage the integration and is considered a trusted vendor resource. - [COMMAND_EXECUTION]: Instructions involve running
membraneCLI commands for logging in and interacting with Freedcamp. These operations are within the expected scope of a project management skill. - [PROMPT_INJECTION]: The skill inherently features an indirect prompt injection surface as it retrieves and processes project data, tasks, and comments from Freedcamp. This is a common characteristic of data-integration skills.
- Ingestion points: Freedcamp task details, issue descriptions, and project metadata fetched via
membrane action runinSKILL.md. - Boundary markers: No specific delimiters are used to wrap external content or instructions to disregard embedded text.
- Capability inventory: The agent can use the CLI to search, create, and modify tasks and projects within the connected Freedcamp account.
- Sanitization: The instructions rely on standard API communication; no manual sanitization of retrieved strings is mentioned.
Audit Metadata