incoming-request-advisor

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data (Slack messages, emails, screenshots, and PDFs) which introduces a risk of indirect prompt injection if those messages contain adversarial instructions.
  • Ingestion points: The skill instructions in SKILL.md explicitly direct the agent to extract text from pasted content, images, and files.
  • Boundary markers: The skill lacks specific instructions to disregard malicious directives that might be embedded within the processed messages.
  • Capability inventory: The skill's functionality is limited to text analysis and drafting; it does not request network access or sensitive file system permissions in its instructions or reference files.
  • Sanitization: No sanitization of input message content is specified before the analysis step.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 03:09 AM
Security Audit — agent-trust-hub — incoming-request-advisor