project-stakeholder-communication
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill processes project-related documents which could be manipulated by an attacker to include hidden instructions designed to influence the drafted communication or the project state.
- Ingestion points:
project_state.md,status-reports.md, andchange-log.md(as defined inSKILL.md). - Boundary markers: Absent; the skill does not utilize delimiters or specific instructions to disregard embedded commands in the source data.
- Capability inventory: The skill is limited to drafting text messages and updating a specific local file (
project_state.md). It lacks network access or shell execution capabilities, which severely limits the impact of an injection. - Sanitization: Absent; there is no evidence of input validation or escaping for the project data provided to the agent.
Audit Metadata