internal-comms

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and summarize data from various corporate and external sources, creating a surface for indirect prompt injection.
  • Ingestion points: The skill retrieves information from Slack channels, Google Drive documents, Emails, Calendar events, and external press articles as specified in examples/3p-updates.md, examples/company-newsletter.md, and examples/faq-answers.md.
  • Boundary markers: The instructions do not include specific delimiters or "ignore embedded instructions" warnings when processing these external inputs.
  • Capability inventory: The skill uses the agent's tools to read sensitive communication data and perform text generation; it does not explicitly invoke dangerous subprocesses or network writes, but it lacks constraints on how the ingested data influences the output.
  • Sanitization: There is no evidence of sanitization, escaping, or filtering of the retrieved content before it is interpolated into the drafting process.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 04:22 PM