internal-comms-community
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and summarize data from various corporate communication platforms, creating a vulnerability surface where malicious instructions embedded in external content could influence the agent.
- Ingestion points: The instructions in
examples/3p-updates.md,examples/company-newsletter.md, andexamples/faq-answers.mddirect the agent to gather context from Slack messages, Google Drive documents, emails, and calendar events. - Boundary markers: The skill lacks explicit instructions for the agent to use delimiters or ignore embedded instructions within the processed data, increasing the risk that the agent might follow commands found in the source material.
- Capability inventory: The skill primarily focuses on drafting content. While it utilizes the agent's toolset to read external data, it does not include its own network operations, file writing, or command execution logic.
- Sanitization: There are no mentioned mechanisms for filtering, validating, or escaping content retrieved from the external sources before it is processed into the final draft.
Audit Metadata