project-management

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses curl command templates to interact with the Spuree API hosted at data.spuree.com. These commands are standard operations for project lifecycle management, including creation, modification, and deletion.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the external Spuree API, which could potentially be used for indirect prompt injection if project or file metadata contains malicious instructions.
  • Ingestion points: Project and item data retrieved from GET /v1/projects and GET /v1/projects/{projectId}/children in SKILL.md.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded content in the retrieved data.
  • Capability inventory: The agent has the ability to create, update, share, and delete project resources through the provided curl templates.
  • Sanitization: There is no explicit sanitization or validation logic described for the data retrieved from the remote API.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 04:00 PM
Security Audit — agent-trust-hub — project-management