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 is designed to process untrusted data from multiple external sources (Slack, Email, Google Drive, Calendar) and summarize it into internal communications.
- Ingestion points: Files
examples/3p-updates.md,examples/company-newsletter.md, andexamples/faq-answers.mdall instruct the agent to crawl Slack messages, emails, and documents to gather context. - Boundary markers: None. The instructions do not provide delimiters or warnings for the agent to ignore potentially malicious instructions embedded in the communications it reads.
- Capability inventory: The skill primarily performs text processing and summarization. It does not contain file-write, network, or subprocess capabilities within the provided files.
- Sanitization: None present. The agent is encouraged to "pull from available sources" and "gather as much context as you can" without validation or escaping of the content found in those external sources.
Audit Metadata