stakeholder-coordination
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its processing of untrusted external content.\n
- Ingestion points: The skill workflow involves reading external materials such as emails, research applications, and contracts (SKILL.md).\n
- Boundary markers: No delimiters or safety instructions are provided to distinguish ingested content from system instructions, which could allow the agent to obey malicious instructions embedded in documents.\n
- Capability inventory: The skill leverages tools with significant capabilities, including file creation (Write), network access (WebSearch/WebFetch), and shell command execution (Bash), increasing the impact of potential injection (SKILL.md).\n
- Sanitization: The instructions do not define any validation or sanitization mechanisms for the data processed from external sources.
Audit Metadata