internal-comms

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • Prompt Injection (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8) due to its core design of summarizing untrusted data from multiple sources.
  • Ingestion points: Slack messages, Google Drive documents, Email content, Calendar events, and External press articles as specified in examples/3p-updates.md and examples/company-newsletter.md.
  • Boundary markers: Absent. The instructions do not define delimiters (like triple-backticks or XML tags) or explicitly command the agent to ignore instructions embedded within the retrieved documents.
  • Capability inventory: The skill requires high-read permissions across core organizational communication and document platforms.
  • Sanitization: Absent. There is no instruction to validate, escape, or filter content retrieved from these sources before it is used in a generated report.
  • No Code (SAFE): This skill consists entirely of Markdown instructions and examples. There are no executable scripts, binaries, or configuration files that could facilitate direct remote code execution or privilege escalation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:44 PM