linkedin-inmail
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill provides instructions for processing external prospect data, creating an indirect prompt injection attack surface.\n
- Ingestion points: External data lists or rows containing prospect information used in batch processing as described in
SKILL.md.\n - Boundary markers: Absent. The skill does not provide instructions to the agent on how to distinguish between data and potential malicious commands within the input.\n
- Capability inventory: Limited to text generation for LinkedIn communications. The skill does not grant access to external tools, system commands, or file system operations.\n
- Sanitization: Absent. There is no instruction to filter or escape the input data.\n- [NO_CODE]: The skill consists entirely of markdown instructions and contains no code or scripts.
Audit Metadata