internal-comms
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from untrusted or multi-user sources such as Slack, email, and shared documents.
- Ingestion points: The files examples/3p-updates.md, examples/company-newsletter.md, and examples/faq-answers.md explicitly instruct the agent to use tools like Slack, Google Drive, and Email to gather content for reports.
- Boundary markers: The skill lacks instructions to use delimiters or "ignore embedded instructions" warnings when processing ingested data.
- Capability inventory: The skill is intended for text generation and summarization; no high-risk command execution tools or external network scripts are defined in the instructions.
- Sanitization: No sanitization, escaping, or validation steps are prescribed for the external content before it is processed or summarized.
Audit Metadata