project-management
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines templates and workflows for processing external data such as GitHub Issues and Pull Request descriptions. This establishes a surface for indirect prompt injection where malicious instructions could be embedded in user-submitted content to influence agent behavior.
- Ingestion points: bug_report.md, feature_request.md, and User Story examples in SKILL.md.
- Boundary markers: The provided templates do not include delimiters or specific instructions to isolate or ignore untrusted content.
- Capability inventory: The skill documents usage of the Linear CLI and suggests integration with project tracking platforms like Jira and GitHub Projects.
- Sanitization: No sanitization or validation logic is defined for the content of the processed templates.
- [COMMAND_EXECUTION]: The documentation includes bash snippets for setting up templates using 'mkdir' and 'cp', and demonstrates usage of the Linear CLI ('linear issue create'). These commands are part of documented project management workflows.
Audit Metadata