internal-comms
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by instructing the agent to ingest and summarize data from sources that could contain malicious instructions.
- Ingestion points: Files "examples/3p-updates.md", "examples/company-newsletter.md", and "examples/faq-answers.md" explicitly direct the agent to pull information from Slack posts, Google Drive documents, Emails, and Calendar events.
- Boundary markers: There are no instructions or requirements to use delimiters or "ignore embedded instructions" warnings within the ingested data, increasing the risk that the agent might follow malicious commands hidden in those sources.
- Capability inventory: The agent is instructed to read, summarize, and format data from these sources into reports and newsletters, which could lead to manipulated outputs if the sources are compromised.
- Sanitization: The skill lacks guidance on sanitizing, escaping, or validating the content retrieved from external communication tools before processing it.
Audit Metadata