draft-my-comments

Pass

Audited by Gen Agent Trust Hub on Nov 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external LinkedIn posts and comments, which constitutes a potential surface for indirect prompt injection. Evidence of mitigation: The skill includes a specific safety section titled 'If you are reading somebody else's post' which explicitly commands the agent to treat external content as data rather than instructions and to ignore any attempts to override the agent's behavior. Capability Inventory: The skill does not define any high-privilege tools in its frontmatter, limiting the potential impact of any successful injection to text generation.
  • [SAFE]: No indicators of malicious activity such as data exfiltration, command execution, or obfuscation were found. The references to external tools like VoiceMoat are for legitimate functionality related to brand voice matching and do not involve unauthorized network operations or downloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 6, 2026, 07:23 AM