pm-monitor-budget
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious code, hardcoded credentials, or unauthorized network activity was detected. The skill follows best practices by failing safely and requesting necessary baseline documentation before making budget judgments.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) due to its integration with external, user-controlled data sources.\n
- Ingestion points: The skill processes data from '.agents/project-context.md', various project management tools (Jira, Linear, Asana, ClickUp), and commercial documents (SOWs, proposals, estimates).\n
- Boundary markers: Absent. The instructions do not specify the use of delimiters or 'ignore' commands to isolate content retrieved from these external sources from the agent's core instructions.\n
- Capability inventory: The skill performs file system reads and uses external tool APIs via the environment's capabilities to aggregate project data.\n
- Sanitization: Absent. The skill uses raw text from external sources for its analytical workflow without explicit validation or content filtering.
Audit Metadata