written-communication

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided drafts and communications to offer structural and logical feedback.
  • Ingestion points: User-supplied text drafts mentioned in the help guidelines (SKILL.md).
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious commands embedded within user drafts.
  • Capability inventory: The skill focuses on text analysis and recommendation; it does not invoke high-privilege tools such as shell execution or network requests within its instructions.
  • Sanitization: There is no evidence of input validation or sanitization for the content being reviewed.
  • [SAFE]: No malicious patterns such as hardcoded credentials, data exfiltration, obfuscation, or unauthorized command execution were detected. All external links point to well-known platforms (YouTube, Substack, Medium, Google Docs, OpenAI) for informational purposes.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 02:49 PM
Security Audit — agent-trust-hub — written-communication