skills/atxinsky/skills/internal-comms/Gen Agent Trust Hub

internal-comms

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is designed to ingest and summarize large volumes of untrusted data from corporate tools like Slack, Email, and Google Drive.
  • Ingestion points: The examples/3p-updates.md, examples/company-newsletter.md, and examples/faq-answers.md files explicitly instruct the agent to gather context from Slack posts, Google Drive documents, and company-wide emails.
  • Boundary markers: None. The instructions do not include delimiters or warnings to treat ingested content as data rather than instructions.
  • Capability inventory: The skill has the capability to read external data and synthesize it into executive-level communications, which could be used to leak sensitive information or misinform leadership if the agent follows instructions hidden within a Slack message or document.
  • Sanitization: There is no mention of sanitizing or filtering the content retrieved from these external tools before it is processed by the LLM.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 04:00 PM
Security Audit — agent-trust-hub — internal-comms